CN105652895A - Mobile robot human body tracking system and tracking method based on laser sensor - Google Patents
Mobile robot human body tracking system and tracking method based on laser sensor Download PDFInfo
- Publication number
- CN105652895A CN105652895A CN201410634552.8A CN201410634552A CN105652895A CN 105652895 A CN105652895 A CN 105652895A CN 201410634552 A CN201410634552 A CN 201410634552A CN 105652895 A CN105652895 A CN 105652895A
- Authority
- CN
- China
- Prior art keywords
- point
- human body
- target
- doubtful
- candidate
- 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
Abstract
The invention provides a mobile robot human body tracking system based on a laser sensor. The system comprises an object detection unit, an object determining unit and a motion control unit. The object detection unit is used for scanning front data and determining a suspected human body object; the object determining unit is used for determining suspected human body object information and obtaining final human body information; and the motion control unit controls motion of a robot body according to determined human body data information. According to the invention, it is ensured that a robot can well realize automatic following under the condition of indoor interference, and at the same time, the following robustness and the tracking precision are improved.
Description
Technical field
The invention belongs to robot field, a kind of mobile apparatus people human tracking system based on laser sensor of special design and tracking method.
Background technology
Target person follow be man-machine interaction study in a hot issue, have a wide range of applications demand in mobile apparatus people field, the main view-based access control model sensor of current existing robot system for tracking, laser range sensor or the method that both combine, the method of view-based access control model sensor is complicated, especially a dependence laser sensor is realized locating the robot with avoidance, it is necessary to increase vision sensor. As adopted single laser sensor, then the collection method of target person is comparatively single, the interference that is subject in environment similar object.
Summary of the invention
The technical problem to be solved in the present invention is to overcome in prior art robot and is vulnerable to the defect of multiple target jamming when human body is followed, a kind of human body follower method based on laser sensor is provided, the method can make robot keep following same target in cases of a disturbance, simple to operate, it is easy to realize.
For solving the problems of the technologies described above, the present invention adopts following technical proposals:
Based on a mobile apparatus people human tracking system for laser sensor, comprise object detection unit, target determination unit and motion control unit; Object detection unit, for scanning preceding data, it is determined that doubtful human body target; Target determination unit, for doubtful human body target information being judged, obtains final human body information; Motion control unit, according to the motion of the somatic data information Control robot body determined.
Preferably, object detection unit comprises scan module, data point conversion module, first judges module and the first screening module; Scan module, for scanning robot preceding data point, and is sent to data point conversion module by the data point of scanning; Data point conversion module, for being converted to the point of the normal data on robot coordinate by data point; First judges module, for filtering out each point set representing obstacle; First screening module, for judging candidate's point set of doubtful human body according to each point set.
Preferably, target determination unit comprises: Object selection module, coordinate transferring, determination module; Object selection module, for choose candidate point collection intermediate point position as doubtful candidate target people position; Coordinate transferring, for transferring doubtful candidate target people position to world system of coordinates coordinate figure; Determination module, in the initial moment, allows real target person stand in the front of robot, using the position of the nearest doubtful candidate target people position of distance robot as the target person finally determined; 2nd scanning period and after, filter out in doubtful target person candidate point the nearest point of the target person candidate point finally determined with upper scan cycle as following target.
The present invention also provides a kind of mobile apparatus people's human body tracing method based on laser sensor, comprises the steps: scanning robot preceding data, it is determined that the data point of doubtful human body target; Doubtful human body target information is judged, obtains final human body information; According to the motion following target information control machine human body determined.
Preferably, described scanning robot preceding data, it is determined that the data point of doubtful human body target is specially: scanning robot preceding data; Described data point is converted to the point of the normal data in robot coordinate system; The point set representing each obstacle is filtered out according to normal data point; Candidate's point set of doubtful human body is judged according to each point set.
Preferably, scanning distance is at 5 meters, and scanning angle is the data within the scope of 180 ��, robot body front.
Preferably, doubtful human body target information being judged, obtaining final human body information concrete steps is: the position getting candidate point collection intermediate point is as doubtful candidate target people position, and is transferred to world's system of coordinates coordinate; After again scanning all candidate's point sets, filter out the nearest candidate point of the target person candidate point finally determined with upper scan cycle as following target.
Adopting technique scheme, the useful effect of the present invention is:
The present invention can realize the function that robot follows human motion automatically, can human body leg feature, movement position at upper a moment according to people gets rid of other jamming target, ensure robot can be good realize independently following in the noisy situation in indoor, improve the robustness and tracking accuracy followed simultaneously.
Accompanying drawing explanation
The robot human body system for tracking structure block diagram that Fig. 1 provides for the embodiment of the present invention;
The robot human body follower method schema that Fig. 2 provides for the embodiment of the present invention.
Embodiment
In order to make the object of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and the specific embodiments, the present invention is further elaborated. It is to be understood that specific embodiment described herein is only in order to explain the present invention, it is not intended to limit the present invention.
Referring to Fig. 1, the principle of work figure of the robot human body system for tracking that Fig. 1 provides for the embodiment of the present invention, comprises object detection unit 110, target determination unit 120 and motion control unit 130. Object detection unit 110 is for scanning preceding data, it is determined that doubtful human body target. Target determination unit 120, for doubtful human body target information being judged, obtains final human body information. Motion control unit 130 is according to the motion of the somatic data information Control robot body 100 determined.
Further, object detection unit 110 comprises scan module 111, data point conversion module 112, first judges module 113 and the first screening module 114.
Scan module 111, for scanning robot preceding data point, and is sent to data point conversion module 112 by the data point of scanning. Described scan module 111 is a laser sensor, and it can scan 270 ��, robot front, angle-resolved rate 0.25 ��, the distance scope all data points within 0.05 meter��30 meters from small to large by scanning angle. As required, the present embodiment only gets distance at 5 meters, and scanning angle is the data point within the scope of 180 ��, robot body front.
Data point conversion module 112, for being converted to the point of the normal data on robot coordinate by data point.
First judges module 113, for filtering out each point set representing obstacle.
First screening module 114, for judging candidate's point set of doubtful human body according to each point set.
Described target determination unit 120 comprises: Object selection module 121, coordinate transferring 122, determination module 123.
Object selection module 121, for choose candidate point collection intermediate point position as doubtful candidate target people position,
Coordinate transferring 122, for transferring doubtful candidate target people position to world system of coordinates coordinate figure;
Determination module 123, in the initial moment, allows real target person stand in the front of robot, using the position of the nearest doubtful candidate target people position of distance robot as the target person finally determined; 2nd scanning period and after, filter out in doubtful target person candidate point the nearest point of the target person candidate point finally determined with upper scan cycle as following target.
It is specially, after scan module 111 scans all candidate's point sets again, compared with the position of the target person that a upper moment determination module 123 is determined, if distance is greater than 1 meter, then deletes this candidate point between the two; If being less than 1 meter, then retain this candidate point. General, owing to the scanning period of laser sensor is very short, therefore the miles of relative movement of human body can not be very big.
Motion control unit 130 is for following target location information, and control machine human body 100 is towards following target motion.
Refer to Fig. 2, the mobile apparatus people's human body tracing method based on laser sensor that Fig. 2 provides for the embodiment of the present invention, comprise the following steps:
Step S10: laser sensor scans robot preceding data, it is determined that the data point of doubtful human body target.
Step S101: laser sensor scans robot preceding data.
In the present embodiment, available laser sensor scans robot preceding data, and it can scan 270 ��, robot front, angle-resolved rate 0.25 ��, the distance scope all data points within 0.05 meter��30 meters from small to large by scanning angle. As required, the present embodiment only gets distance at 5 meters, and scanning angle is the data point within the scope of 180 ��, robot body front. Laser sensor is arranged on robot body, 0.23 meter, distance ground.
Step S102: described data point is converted to the point of the normal data in robot coordinate system.
Step S103: filter out the point set representing each obstacle according to normal data point.
Concrete grammar is: the distance calculating adjacent two normal data point one by one, if being greater than a threshold value, then illustrate that these two normal data points are not same obstacle, two data points are divided into two point sets, 2nd data point again with next data point calculation distance, adopt same method to sort out. After traveling through whole data point like this, all data points can being divided into some point sets, each point set represents an obstacle. Herein, threshold value is generally 0.03 meter.
Step S104: the candidate's point set judging doubtful human body according to each point set.
Judge the distance of the head and the tail data point of each point set successively, if distance in the scope of 0.05 meter-0.4 meter, then gets this point set alternatively point set. It can be appreciated that may occur the obstacle such as multiple people or table chair in surrounding space, therefore, this candidate's point set may be multiple.
Step S20: doubtful human body target information is judged, obtains final human body information;
Step S201: the position getting candidate point collection intermediate point is as doubtful candidate target people position;
Step S202: transfer doubtful candidate target people position to world system of coordinates coordinate figure;
Step S203: after scanning obtains all candidate's point sets again, filters out the nearest point of the positional distance of scan cycle target person as following target.
The initial moment, real target person is allowed to stand in the front of robot, using the position of the nearest candidate point of distance robot as target person, after scan module 111 scans all candidate's point sets again, compared with the position of a upper moment target person, if distance is greater than 1 meter, then delete this candidate point between the two; If being less than 1 meter, then retain this candidate point. General, owing to the scanning period of laser sensor is very short, therefore the miles of relative movement of human body can not be very big. The all candidate points retained filter out the nearest point of the positional distance of scan cycle target person as following target.
It is appreciated that, due to robot under complex environment, follow goal task collision-free motion time, the process of following has the appearance of dynamic disturbance people, may at a time there is no the candidate point in threshold value (1 meter) scope, as this situation occurs, using the candidate point position in a upper moment as following target.
Step S30: according to the motion following target information control machine human body determined.
After determining to follow target, follow the motion of target location information data control according to this.
The above, it it is only the better embodiment of the present invention, not the present invention is done any restriction in form, although the present invention discloses as above with better embodiment, but and be not used to limit the present invention, any those skilled in the art, do not departing within the scope of technical solution of the present invention, make a little change when the technology contents of above-mentioned announcement can be utilized or it is modified to the equivalent embodiment of equivalent variations, in every case it is do not depart from technical solution of the present invention content, the any simple modification above embodiment done according to the technical spirit of the present invention, equivalent variations and modification, all still belong in the scope of technical solution of the present invention.
Claims (7)
1. the mobile apparatus people human tracking system based on laser sensor, it is characterised in that, comprise object detection unit, target determination unit and motion control unit;
Object detection unit, for scanning preceding data, it is determined that doubtful human body target;
Target determination unit, for doubtful human body target information being judged, obtains final human body information;
Motion control unit, according to the motion of the somatic data information Control robot body determined.
2. human tracking system as claimed in claim 1, it is characterised in that, described object detection unit comprises scan module, data point conversion module, first judges module and the first screening module;
Scan module, for scanning robot preceding data point, and is sent to data point conversion module by the data point of scanning;
Data point conversion module, for being converted to the point of the normal data on robot coordinate by data point;
First judges module, for filtering out each point set representing obstacle;
First screening module, for judging candidate's point set of doubtful human body according to each point set.
3. human tracking system as claimed in claim 1, it is characterised in that, described target determination unit comprises: Object selection module, coordinate transferring, determination module;
Object selection module, for choose candidate point collection intermediate point position as doubtful candidate target people position; Coordinate transferring, for transferring doubtful candidate target people position to world system of coordinates coordinate figure;
Determination module, in the initial moment, allows real target person stand in the front of robot, using the position of the nearest doubtful candidate target people position of distance robot as the target person finally determined; 2nd scanning period and after, filter out in doubtful target person candidate point the nearest point of the target person candidate point finally determined with upper scan cycle as following target.
4. the mobile apparatus people's human body tracing method based on laser sensor, it is characterised in that, comprise the steps:
Scanning robot preceding data, it is determined that the data point of doubtful human body target;
Doubtful human body target information is judged, obtains final human body information;
According to the motion following target information control machine human body determined.
5. as claimed in claim 4 based on mobile apparatus people's human body tracing method of laser sensor, it is characterised in that, described scanning robot preceding data, it is determined that the data point of doubtful human body target is specially:
Scanning robot preceding data;
Described data point is converted to the point of the normal data in robot coordinate system;
The point set representing each obstacle is filtered out according to normal data point;
Candidate's point set of doubtful human body is judged according to each point set.
6. as claimed in claim 5 based on mobile apparatus people's human body tracing method of laser sensor, it is characterised in that, scanning distance is at 5 meters, and scanning angle is the data within the scope of 180 ��, robot body front.
7. as claimed in claim 4 based on mobile apparatus people's human body tracing method of laser sensor, it is characterised in that, described doubtful human body target information is judged, obtaining final human body information concrete steps is:
The position getting candidate point collection intermediate point is as doubtful candidate target people position, and is transferred to world's system of coordinates coordinate;
After again scanning all candidate's point sets, filter out the nearest candidate point of the target person candidate point finally determined with upper scan cycle as following target.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410634552.8A CN105652895A (en) | 2014-11-12 | 2014-11-12 | Mobile robot human body tracking system and tracking method based on laser sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410634552.8A CN105652895A (en) | 2014-11-12 | 2014-11-12 | Mobile robot human body tracking system and tracking method based on laser sensor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105652895A true CN105652895A (en) | 2016-06-08 |
Family
ID=56483877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410634552.8A Pending CN105652895A (en) | 2014-11-12 | 2014-11-12 | Mobile robot human body tracking system and tracking method based on laser sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105652895A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106054894A (en) * | 2016-07-05 | 2016-10-26 | 北京九星智元科技有限公司 | Robot accompanying system, robot accompanying method and robot trolley |
| CN106203361A (en) * | 2016-07-15 | 2016-12-07 | 苏州宾果智能科技有限公司 | A kind of robotic tracking's method and apparatus |
| CN106774303A (en) * | 2016-10-12 | 2017-05-31 | 纳恩博（北京）科技有限公司 | A kind of method for tracing and tracing equipment |
| CN107009343A (en) * | 2017-05-03 | 2017-08-04 | 山东大学 | A kind of banking assistant robot based on many biometric informations |
| CN107367733A (en) * | 2017-07-20 | 2017-11-21 | 上海脉泽光电科技有限公司 | A kind of combination GPS distance-finding method and its range unit |
| CN107544506A (en) * | 2017-09-27 | 2018-01-05 | 上海有个机器人有限公司 | Robot follower method, robot and storage medium |
| CN108121359A (en) * | 2016-11-29 | 2018-06-05 | 沈阳新松机器人自动化股份有限公司 | A kind of shopping robot |
| CN108717302A (en) * | 2018-05-14 | 2018-10-30 | 平安科技（深圳）有限公司 | Robot follows personage's method, apparatus and storage medium, robot |
| CN109164433A (en) * | 2018-08-22 | 2019-01-08 | 中国北方车辆研究所 | A kind of scouting countermeasure set and method based on single laser source |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060140450A1 (en) * | 2004-12-14 | 2006-06-29 | Samsung Electronics Co., Ltd. | Human tracking apparatus and method, storage medium storing program executing the method, and mobile electronic system including the apparatus |
| CN102253391A (en) * | 2011-04-19 | 2011-11-23 | 浙江大学 | Multi-laser-radar-based pedestrian target tracking method |
| CN102411368A (en) * | 2011-07-22 | 2012-04-11 | 北京大学 | Active vision human face tracking method and tracking system of robot |
| CN102411371A (en) * | 2011-11-18 | 2012-04-11 | 浙江大学 | Multi-sensor service-based robot following system and method |
| CN103268616A (en) * | 2013-04-18 | 2013-08-28 | 北京工业大学 | Multi-feature multi-sensor method for mobile robot to track moving body |
| CN103345752A (en) * | 2013-06-17 | 2013-10-09 | 中国人民解放军总参谋部第六十一研究所 | Method for tracking pedestrian by cooperating robot and mobile phone |
-
2014
- 2014-11-12 CN CN201410634552.8A patent/CN105652895A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060140450A1 (en) * | 2004-12-14 | 2006-06-29 | Samsung Electronics Co., Ltd. | Human tracking apparatus and method, storage medium storing program executing the method, and mobile electronic system including the apparatus |
| CN102253391A (en) * | 2011-04-19 | 2011-11-23 | 浙江大学 | Multi-laser-radar-based pedestrian target tracking method |
| CN102411368A (en) * | 2011-07-22 | 2012-04-11 | 北京大学 | Active vision human face tracking method and tracking system of robot |
| CN102411371A (en) * | 2011-11-18 | 2012-04-11 | 浙江大学 | Multi-sensor service-based robot following system and method |
| CN103268616A (en) * | 2013-04-18 | 2013-08-28 | 北京工业大学 | Multi-feature multi-sensor method for mobile robot to track moving body |
| CN103345752A (en) * | 2013-06-17 | 2013-10-09 | 中国人民解放军总参谋部第六十一研究所 | Method for tracking pedestrian by cooperating robot and mobile phone |
Non-Patent Citations (1)
| Title |
|---|
| 王灿 等: "基于激光雷达机器人的目标人跟踪方法研究", 《计算机应用与软件》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106054894A (en) * | 2016-07-05 | 2016-10-26 | 北京九星智元科技有限公司 | Robot accompanying system, robot accompanying method and robot trolley |
| CN106054894B (en) * | 2016-07-05 | 2019-04-09 | 北京九星智元科技有限公司 | A kind of robot adjoint system, adjoint method and robot car |
| CN106203361A (en) * | 2016-07-15 | 2016-12-07 | 苏州宾果智能科技有限公司 | A kind of robotic tracking's method and apparatus |
| CN106774303A (en) * | 2016-10-12 | 2017-05-31 | 纳恩博（北京）科技有限公司 | A kind of method for tracing and tracing equipment |
| CN106774303B (en) * | 2016-10-12 | 2019-04-02 | 纳恩博（北京）科技有限公司 | A kind of method for tracing and tracing equipment |
| CN108121359A (en) * | 2016-11-29 | 2018-06-05 | 沈阳新松机器人自动化股份有限公司 | A kind of shopping robot |
| CN107009343A (en) * | 2017-05-03 | 2017-08-04 | 山东大学 | A kind of banking assistant robot based on many biometric informations |
| CN107367733A (en) * | 2017-07-20 | 2017-11-21 | 上海脉泽光电科技有限公司 | A kind of combination GPS distance-finding method and its range unit |
| CN107544506A (en) * | 2017-09-27 | 2018-01-05 | 上海有个机器人有限公司 | Robot follower method, robot and storage medium |
| CN107544506B (en) * | 2017-09-27 | 2021-05-18 | 上海有个机器人有限公司 | Robot following method, robot, and storage medium |
| CN108717302A (en) * | 2018-05-14 | 2018-10-30 | 平安科技（深圳）有限公司 | Robot follows personage's method, apparatus and storage medium, robot |
| WO2019218526A1 (en) * | 2018-05-14 | 2019-11-21 | 平安科技（深圳）有限公司 | Method for robot to follow human, and apparatus, storage medium, and robot |
| CN108717302B (en) * | 2018-05-14 | 2021-06-25 | 平安科技（深圳）有限公司 | Method and device for robot to follow person, storage medium and robot |
| CN109164433A (en) * | 2018-08-22 | 2019-01-08 | 中国北方车辆研究所 | A kind of scouting countermeasure set and method based on single laser source |
| CN109164433B (en) * | 2018-08-22 | 2023-07-25 | 中国北方车辆研究所 | Device and method for detecting interference based on single laser source |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105652895A (en) | Mobile robot human body tracking system and tracking method based on laser sensor | |
| CN104536009B (en) | Above ground structure identification that a kind of laser infrared is compound and air navigation aid | |
| CN103268616B (en) | The moveable robot movement human body tracing method of multi-feature multi-sensor | |
| CN103500322B (en) | Automatic lane line identification method based on low latitude Aerial Images | |
| CN105872477A (en) | Video monitoring method and system | |
| CN102609934A (en) | Multi-target segmenting and tracking method based on depth image | |
| CN106227218A (en) | The navigation barrier-avoiding method of a kind of Intelligent mobile equipment and device | |
| US20200110173A1 (en) | Obstacle detection method and device | |
| CN104751146B (en) | A kind of indoor human body detection method based on 3D point cloud image | |
| CN103477352A (en) | Gesture recognition using depth images | |
| CN105930795A (en) | Walking state identification method based on space vector between human body skeleton joints | |
| CN105551082A (en) | Method and device of pavement identification on the basis of laser-point cloud | |
| CN107014294A (en) | A kind of contact net geometric parameter detection method and system based on infrared image | |
| CN107792115A (en) | One kind automatically extracts both wired rail crest level methods using three-dimensional laser point cloud | |
| CN107610157B (en) | Unmanned aerial vehicle target tracking method and system | |
| CN108664841A (en) | A kind of sound state object recognition methods and device based on laser point cloud | |
| CN103472907B (en) | Method and system for determining operation area | |
| CN104287946A (en) | Device and method for prompting blind persons to avoid obstacles | |
| CN102509074A (en) | Target identification method and device | |
| CN111079518B (en) | Ground-falling abnormal behavior identification method based on law enforcement and case handling area scene | |
| CN106156758B (en) | A kind of tidal saltmarsh method in SAR seashore image | |
| CN110210452A (en) | It is a kind of based on improve tiny-yolov3 mine truck environment under object detection method | |
| Almansa-Valverde et al. | Mobile robot map building from time-of-flight camera | |
| CN107791251A (en) | robot movement control method and robot | |
| CN110147748A (en) | A kind of mobile robot obstacle recognition method based on road-edge detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160608 |