CN114577215B - Method, equipment and medium for updating characteristic map of mobile robot - Google Patents
Method, equipment and medium for updating characteristic map of mobile robot Download PDFInfo
- Publication number
- CN114577215B CN114577215B CN202210236656.8A CN202210236656A CN114577215B CN 114577215 B CN114577215 B CN 114577215B CN 202210236656 A CN202210236656 A CN 202210236656A CN 114577215 B CN114577215 B CN 114577215B
- Authority
- CN
- China
- Prior art keywords
- feature
- feature points
- points
- point
- map
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 230000000875 corresponding effect Effects 0.000 description 25
- 230000008569 process Effects 0.000 description 21
- 238000005516 engineering process Methods 0.000 description 6
- 238000010276 construction Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000003550 marker Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
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
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3807—Creation or updating of map data characterised by the type of data
- G01C21/3811—Point data, e.g. Point of Interest [POI]
-
- 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
- G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The embodiment of the specification discloses a method, equipment and medium for updating a characteristic map of a mobile robot, wherein the method comprises the following steps: acquiring point cloud data of the mobile robot at the current moment, and generating a current feature point set according to a plurality of feature points in the point cloud data; respectively carrying out nearest neighbor matching on a plurality of characteristic points in the current characteristic point set and the preset characteristic points in the initialized characteristic map; dividing a plurality of feature points in a current feature point set into a first type feature point and a second type feature point according to a matching result of nearest neighbor matching, and updating the positions of corresponding feature points matched with the first type feature point in a preset initialization feature map according to the position information of the first type feature point acquired in advance to generate a first feature map; and adding each feature point in the second type of feature points to the first feature map according to the pre-acquired position information of the second type of feature points, and generating an updated feature map.
Description
Technical Field
The present disclosure relates to the field of robots, and in particular, to a method, an apparatus, and a medium for updating a feature map of a mobile robot.
Background
Along with the development of the scientific technology, the application field of the mobile robot is gradually expanded, the working environment faced by the mobile robot is also more and more complex, the realization of autonomous navigation of the robot is an important step for solving the problems generated by various complex working environments, the construction of a map of the mobile robot is a key technology in the mobile robot technology, and the construction of a characteristic map directly relates to the accuracy and the stability of the mobile robot in the subsequent positioning process.
In an application scene of an indoor mobile robot, a single-line laser radar is often adopted to scan surrounding environment features such as circular arcs, line segments, corner points and the like for recording, and the features are stored in a feature map. However, during the movement of the mobile robot, redundant features may be scanned, for example, features scanned from dynamic obstacles, features blocked by other obstacles, and the like. Because the scanned features may have redundant features, the updated feature map has poor quality, and stability and accuracy in the subsequent positioning process are affected.
Disclosure of Invention
One or more embodiments of the present disclosure provide a method, an apparatus, and a medium for updating a feature map of a mobile robot, which are used to solve the following technical problems: because the scanned features may have redundant features, the updated feature map has poor quality, and stability in the subsequent positioning process is affected.
One or more embodiments of the present disclosure adopt the following technical solutions:
one or more embodiments of the present specification provide a feature map updating method of a mobile robot, the method including: acquiring point cloud data of a mobile robot at the current moment, and generating a current feature point set according to a plurality of feature points in the point cloud data, wherein the point cloud data comprises a plurality of feature points; performing nearest neighbor matching on a plurality of feature points in the current feature point set and feature points in a preset initialization feature map, wherein the preset initialization feature map is an initialization feature map corresponding to the last time of the current time; dividing a plurality of feature points in the current feature point set into a first type of feature points and a second type of feature points according to the matching result of the nearest neighbor matching, wherein the feature points in the first type of feature points are respectively matched with the corresponding feature points in the initialized feature map, and the feature points in the second type of feature points are not matched with the feature points in the initialized feature map; updating the position information of the corresponding feature points matched with the first type of feature points in the preset initialization feature map according to the pre-acquired position information of the first type of feature points, so as to generate a first feature map; and adding each feature point in the second type of feature points to the first feature map according to the pre-acquired position information of the second type of feature points, and generating an updated feature map.
Further, before the plurality of feature points in the current feature point set are respectively matched with the feature points in the preset initialization feature map in a nearest neighbor manner, the method further includes: acquiring a plurality of characteristic points in point cloud data of the mobile robot at a moment previous to the current moment; and initializing and defining each characteristic point in the plurality of characteristic points, and generating the initialized characteristic map.
Further, the initializing and defining each feature point in the plurality of feature points specifically includes: acquiring feature types of each feature point in the plurality of feature points, and defining the feature types of each feature point in the plurality of feature points according to the feature types of each feature point, wherein the feature types comprise arc types and corner types; acquiring global position coordinates of each feature point in the plurality of feature points, and defining position information of each feature point according to the global position coordinates of each feature point; setting the theoretical observation times and the effective observation times of each of the plurality of feature points as initial values; each feature point of the plurality of feature points is defined as an untrusted landmark.
Further, the performing nearest neighbor matching on the plurality of feature points in the current feature point set and feature points in the preset initialized feature map respectively specifically includes: acquiring position information of each feature point in the initialized feature map; and carrying out nearest neighbor matching on the plurality of feature points in the current feature point set and the position information of each feature point in the initialized feature map one by one.
Further, the step of dividing the plurality of feature points in the current feature point set into a first type feature point and a second type feature point according to the matching result of the nearest neighbor matching specifically includes: if a specified feature point exists in a plurality of feature points in the current feature point set, and the distance between the specified feature point and a corresponding feature point in the initialized feature map is smaller than a preset threshold, judging that the matching result of the nearest neighbor matching is successful, and taking the specified feature point as a first type feature point; if a current feature point exists in the plurality of feature points in the current feature point set, and the distance between the current feature point and any one feature point in the initialized feature map is larger than or equal to a preset threshold value, judging that the matching result of the nearest neighbor matching is unsuccessful, and taking the current feature point as a second type feature point.
Further, the updating, according to the pre-acquired position information of the first type of feature points, the position information of the corresponding feature points matched with the first type of feature points in the pre-set initialization feature map, to generate a first feature map specifically includes: acquiring the position information of each feature point in the first type of feature points as first position information; acquiring position information of each current feature point matched with each feature point in the first type of feature points in the preset initialization feature map as second position information; updating the position information of each current feature point according to the first position information and the second position information, and generating the position information of each current feature point so as to update the position information of each current feature point; and setting the effective observation times of each current feature point matched with each feature point in the first type feature points in the preset initialization feature map to be an initial value plus one so as to update the effective observation times and generate updated effective observation times of each current feature point.
Further, after the generating the updated feature map, the method further includes: generating an effective observation rate of each feature point in the updated feature map according to the ratio of the effective observation times to the theoretical observation times of each feature point in the updated feature map; judging whether feature points to be removed exist in the feature points in the updated feature map or not according to the effective observation times of the feature points in the updated feature map and the effective observation rate of the feature points in the updated feature map, wherein the effective observation times of the feature points to be removed after updating are smaller than a first preset threshold value, and the effective observation rate is smaller than a second preset threshold value; and when the feature points to be removed exist in the updated feature map, removing the feature points to be removed from the updated feature map.
Further, after the generating the updated feature map, the method further includes: if a first feature point exists in each feature point in the updated feature map, and the updated effective observation times are larger than or equal to a first preset threshold value, updating the first feature point from an untrusted landmark to a trusted landmark.
One or more embodiments of the present specification provide a feature map updating apparatus of a mobile robot, including:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring point cloud data of a mobile robot at the current moment, and generating a current feature point set according to a plurality of feature points in the point cloud data, wherein the point cloud data comprises a plurality of feature points; performing nearest neighbor matching on a plurality of feature points in the current feature point set and feature points in a preset initialization feature map, wherein the preset initialization feature map is an initialization feature map corresponding to the last time of the current time; dividing a plurality of feature points in the current feature point set into a first type of feature points and a second type of feature points according to the matching result of the nearest neighbor matching, wherein the feature points in the first type of feature points are respectively matched with the corresponding feature points in the initialized feature map, and the feature points in the second type of feature points are not matched with the feature points in the initialized feature map; updating the position information of the corresponding feature points matched with the first type of feature points in the preset initialization feature map according to the pre-acquired position information of the first type of feature points, so as to generate a first feature map; and adding each feature point in the second type of feature points to the first feature map according to the pre-acquired position information of the second type of feature points, and generating an updated feature map.
One or more embodiments of the present specification provide a non-volatile computer storage medium storing computer-executable instructions configured to: acquiring point cloud data of a mobile robot at the current moment, and generating a current feature point set according to a plurality of feature points in the point cloud data, wherein the point cloud data comprises a plurality of feature points; performing nearest neighbor matching on a plurality of feature points in the current feature point set and feature points in a preset initialization feature map, wherein the preset initialization feature map is an initialization feature map corresponding to the last time of the current time; dividing a plurality of feature points in the current feature point set into a first type of feature points and a second type of feature points according to the matching result of the nearest neighbor matching, wherein the feature points in the first type of feature points are respectively matched with the corresponding feature points in the initialized feature map, and the feature points in the second type of feature points are not matched with the feature points in the initialized feature map; updating the position information of the corresponding feature points matched with the first type of feature points in the preset initialization feature map according to the pre-acquired position information of the first type of feature points, so as to generate a first feature map; and adding each feature point in the second type of feature points to the first feature map according to the pre-acquired position information of the second type of feature points, and generating an updated feature map.
The above-mentioned at least one technical scheme that this description embodiment adopted can reach following beneficial effect: according to the technical scheme, the inherent attribute is defined for each feature to initialize the feature map, the feature points in the current feature point set are divided into the matchable feature and the new feature through the matching of the current feature point set and the initialized feature map, a Kalman filter is independently built for each feature point, the updating of each feature is tracked, the updating of each feature is evaluated and removed according to the historical observation effect of the feature, the calculation memory is saved, the stability of the feature map is greatly improved, the map building quality of the robot is guaranteed, and the positioning and obstacle avoidance capability is improved.
Drawings
In order to more clearly illustrate the embodiments of the present description or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some of the embodiments described in the present description, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
Fig. 1 is a flow chart of a method for updating a feature map of a mobile robot according to an embodiment of the present disclosure;
fig. 2 is a flowchart of another method for updating a feature map of a mobile robot according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a feature map updating apparatus of a mobile robot according to an embodiment of the present disclosure.
Detailed Description
In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present disclosure.
Along with the development of the scientific technology, the application field of the mobile robot is gradually expanded, the working environment faced by the mobile robot is also more and more complex, the realization of autonomous navigation of the robot is an important step for solving the problems generated by various complex working environments, the construction of a map of the mobile robot is a key technology in the mobile robot technology, and the construction of a characteristic map directly relates to the accuracy and the stability of the mobile robot in the subsequent positioning process.
In an application scene of an indoor mobile robot, a single-line laser radar is often adopted to scan surrounding environment features such as circular arcs, line segments, corner points and the like for recording, and the features are stored in a feature map. However, during the movement of the mobile robot, redundant features may be scanned, for example, features scanned from dynamic obstacles, features blocked by other obstacles, and the like. Because the scanned features may have redundant features, the updated feature map has poor quality, and stability and accuracy in the subsequent positioning process are affected.
The embodiment of the specification provides a feature map updating method of a mobile robot, and an execution subject may be a server or any device with data processing capability. Fig. 1 is a flow chart of a method for updating a feature map of a mobile robot according to an embodiment of the present disclosure, as shown in fig. 1, the method mainly includes the following steps:
step S101, obtaining point cloud data of the mobile robot at the current moment, and generating a current feature point set according to a plurality of feature points in the point cloud data.
In one embodiment of the present disclosure, the point cloud data of the mobile robot at the current moment is acquired by the laser radar, and the point cloud data acquired by the laser radar is different at different moments along with the movement of the robot due to the fact that the mobile robot is in a moving state. After the point cloud data at the current moment is obtained, after the features are extracted from the point cloud data, a plurality of feature points are generated, and the plurality of feature points in the point cloud data form a current feature point set.
Step S102, a plurality of feature points in the current feature point set are respectively matched with feature points in a preset initialization feature map in a nearest neighbor mode.
The preset initialization feature map is an initialization feature map corresponding to the previous moment of the current moment.
And respectively carrying out nearest neighbor matching on a plurality of characteristic points in the current characteristic point set and the characteristic points in the preset initialization characteristic map, and further comprising: acquiring a plurality of characteristic points in point cloud data of a mobile robot at a moment previous to the current moment; initializing and defining each feature point in a plurality of feature points, and generating the initialized feature map specifically comprises the following steps: acquiring feature types of each feature point in a plurality of feature points, and defining the feature types of each feature point in the plurality of feature points according to the feature types of each feature point, wherein the feature types comprise arc types and corner types; acquiring global position coordinates of each feature point in the plurality of feature points, and defining position information of each feature point according to the global position coordinates of each feature point; setting the theoretical observation times and the effective observation times of each of the plurality of feature points as initial values; each feature point of the plurality of feature points is defined as an untrusted landmark.
In one embodiment of the present description, the feature map needs to be initialized, and an initialized feature map is generated, where the default is that the feature map exists, and only the feature map needs to be updated. There may be a case where there is no feature map, and when the feature map is not present, the initialization may be performed using the first frame point cloud feature point set. It should be noted that, the initialization here is to initially define the inherent attribute of each feature, and the attribute of a certain feature not only indicates the distinction between other features, but also includes the variation trend and the behavior of the feature in multiple historical observations. And acquiring point cloud data of the mobile robot at the moment previous to the current moment, extracting features from the point cloud data to obtain a plurality of feature points, initializing and defining each feature point in the plurality of feature points, and generating the initialized feature map.
In one embodiment of the present description, initializing the definition of each of the plurality of feature points includes defining a feature type, defining location information, defining a theoretical number of observations, a number of valid observations, and whether the feature point is a trusted landmark. Wherein the location information may also be represented by global coordinates.
In one embodiment of the present specification, a feature type of each feature point is obtained, wherein the feature type includes a circular arc and a corner point, and each feature is defined according to the feature type of each feature point. For example, the feature point a is a circular arc class, and the feature point B is a corner class. So as to facilitate matching and updating according to the same type of feature points in the subsequent matching and updating process, and improve the operation efficiency.
In one embodiment of the present specification, global coordinates, i.e., position information, of each feature point are acquired, and the global coordinates are recorded in the position information attribute of each feature point for use in subsequent updating and matching. If a certain feature point should be detected in theory in the laser radar detection range, the value of the theoretical observation number is increased by one, and similarly, the effective observation number is the value of the effective observation number increased by one when the feature point is detected in a new laser scan when the feature matching in the new feature point set is successful or correlated. In addition, in the actual observation process, the shielding of other obstacles and the failure of observing the characteristic points of the sample can not meet the requirements, and the failure of characteristic extraction and other special conditions can possibly cause the condition that the detected characteristic points are not detected, so that the effective observation degree of the characteristic points can be represented by setting an effective observation rate, wherein the effective observation rate is the ratio of the effective observation times to the theoretical observation times. Finally, a matchable flag for each feature point needs to be set, and the matchable flag is used to determine whether the feature point is a trusted landmark. If the feature point is a landmark marker, the matchable marker is set to 1, otherwise, to 0.
Since in one embodiment of the present specification, the initialization definition is performed by the first feature point set, that is, the feature point scanned for the first time, the theoretical number of observations, the effective number of observations, and the effective observation rate are all set to 1. The feature points in the feature point set obtained by initial scanning cannot judge whether the feature points are trusted landmarks or not, and the feature points can be determined by multiple scanning and detection, so that the matchable mark can be set to be 0.
Specifically, the method for performing nearest neighbor matching on a plurality of feature points in a current feature point set and feature points in a preset initialization feature map respectively includes: acquiring position information of each feature point in an initialized feature map; and carrying out nearest neighbor matching on a plurality of feature points in the current feature point set and position information of each feature point in the initialized feature map one by one.
In one embodiment of the present specification, position information of each feature point in an initialized feature map is acquired, and a plurality of feature points in a current feature point set are acquired. And carrying out nearest neighbor matching on a plurality of feature points in the current feature point set and each feature point in the initialized map one by one. The nearest neighbor matching refers to determining whether the feature points meeting the distance requirement exist in the two feature point sets by using a nearest neighbor algorithm. For example, there are 10 feature points in the initialized feature map, there are 5 feature points in the current feature point set, the 5 feature points in the current feature point set are taken out to be the first one, and are respectively matched with 10 feature points in the initialized feature map in a nearest-neighbor manner, whether the 10 feature points in the initialized feature map have feature points nearest to the first feature point or not is judged, and the like, and the 5 feature points in the current feature point set are matched in a nearest-neighbor manner.
Step S103, dividing the plurality of feature points in the current feature point set into a first type feature point and a second type feature point according to the matching result of nearest neighbor matching.
The characteristic points in the first type of characteristic points are respectively matched with the corresponding characteristic points in the initialized characteristic map, and the characteristic points in the second type of characteristic points are not matched with the characteristic points in the initialized characteristic map;
specifically, according to a matching result of nearest neighbor matching, dividing a plurality of feature points in a current feature point set into a first type feature point and a second type feature point, specifically including: if the specified feature points exist in the plurality of feature points in the current feature point set, and the distance between the specified feature points and the corresponding feature points in the initialized feature map is smaller than a preset threshold, judging that the matching result of nearest neighbor matching is successful, and taking the specified feature points as first type feature points; if the current feature point exists in the plurality of feature points in the current feature point set, the distance between the current feature point and any one feature point in the initialized feature map is larger than or equal to a preset threshold value, the matching result of nearest neighbor matching is judged to be unsuccessful, and the current feature point is taken as a second type feature point.
In one embodiment of the present disclosure, if a plurality of feature points in a current feature point set are respectively subjected to nearest neighbor matching with feature points in a preset initialized feature map, and then specified feature points exist in the plurality of feature points in the current feature point set, and the distance between the specified feature points and corresponding feature points in the initialized feature map is smaller than a preset threshold, then a matching result of nearest neighbor matching is determined to be successful, and the specified feature points are used as first-class feature points. For example, the current feature point set includes feature point a, feature point B, feature point C, feature point D, and feature point E, after nearest neighbor matching, there are feature point A1, feature point B1, and feature point C1 in the initialized feature map that are respectively matched with feature point a, feature point B, and feature point C, that is, the distance between feature point a and feature point A1 is smaller than a preset distance, the distance between feature point B and feature point B1 is smaller than a preset distance, the distance between feature point C and feature point C1 is smaller than a preset distance, and the preset distance here may be set to 0.1 meter, so that feature point a, feature point B, and feature point C are the first type of feature points.
If the current feature point exists in the plurality of feature points in the current feature point set, the distance between the current feature point and any one feature point in the initialized feature map is larger than or equal to a preset threshold value, the matching result of nearest neighbor matching is judged to be unsuccessful, and the current feature point is taken as a second type feature point. Continuing with the above example, no feature point matching the feature point D and the feature point E is found in the initialized feature map, that is, the distance between the feature point D and each feature point in the initialized feature map is greater than or equal to the preset threshold, and similarly, the distance between the feature point E and each feature point in the initialized feature map is greater than or equal to the preset threshold, so that the feature point D and the feature point E are regarded as the second type feature point, and may be defined as a new feature point.
Step S104, according to the pre-acquired position information of the first type of feature points, updating the position information of the corresponding feature points matched with the first type of feature points in the pre-set initialization feature map to generate a first feature map.
Specifically, according to the pre-acquired position information of the first type of feature points, in a pre-set initialization feature map, updating the position information of the corresponding feature points matched with the first type of feature points to generate a first feature map, which specifically includes: acquiring position information of each feature point in the first type of feature points as first position information; acquiring position information of each current feature point matched with each feature point in the first type of feature points in a preset initialization feature map as second position information; updating the position information of each current feature point according to the first position information and the second position information, and generating the position information of each current feature point so as to update the position information of each current feature point; and setting the effective observation times of each current feature point matched with each feature point in the first type of feature points in the preset initialization feature map to be one plus the initial value so as to update the effective observation times and generate updated effective observation times of each current feature point.
In one embodiment of the present disclosure, after determining the matched feature point and the new feature point in the current feature point set, the attribute information of the matched feature point in the initialized feature map needs to be updated. First is the update of the location information. Acquiring position information of each feature point in the first type of feature points as first position information; and acquiring the position information of each current feature point matched with each feature point in the first type of feature points in the preset initialization feature map as second position information. In order to increase the accuracy of the position information of the feature points, the position information of each current feature point is updated through the first position information and the second position information corresponding to adjacent moments, and the position information of each current feature point is generated so as to update the position information of each current feature point. In addition, there are feature points in the current feature point set, which are matched with feature points in the initialized feature map, to show that the feature points are actually scanned twice, so that the effective observation times of the current feature points matched with the feature points in the first type of feature points in the preset initialized feature map are set to be one plus the initial value, so that the effective observation times are updated, and the updated effective observation times of the current feature points are generated.
It should be noted that, the location information may be represented by using a state quantity, and in the process of initializing the feature map and generating the initialized feature map, a kalman filter is established for each feature in the initialized feature map, that is, the state quantity of each feature is independently established and tracked, so as to implement feature update of each feature point.
Step S105, adding each feature point in the second type feature points to the first feature map according to the pre-acquired position information of the second type feature points, and generating an updated feature map.
In the actual application process, the feature points scanned by the mobile robot at the previous moment and the current moment are different, and new scanned feature points may exist. It is therefore necessary to add the newly scanned feature points to the first feature map.
In one embodiment of the present disclosure, the location information of each feature point in the second class of feature points is obtained, each feature point in the second class of feature points is added to the first feature map according to the location information of each feature point in the second class of feature points, and attribute definition is performed on all feature points in the second class of feature points according to an initialization process of initializing the feature map.
After generating the updated feature map, the method further comprises: generating the effective observation rate of each feature point in the updated feature map according to the ratio of the effective observation times to the theoretical observation times of each feature point in the updated feature map; judging whether feature points to be removed exist in the feature points in the updated feature map or not according to the effective observation times of the feature points in the updated feature map and the effective observation rate of the feature points in the updated feature map, wherein the effective observation times of the feature points to be removed after updating are smaller than a first preset threshold value, and the effective observation rate is smaller than a second preset threshold value; and when the feature points to be removed exist in the updated feature map, removing the feature points to be removed from the updated feature map.
In the mobile robot mapping process, the observation effect of some characteristics may be very poor, and the reasons include: features detected from dynamic obstacles or blocked by other obstacles, and other special situations such as sudden increase of laser radar errors, feature identification errors, and disturbance of robot positioning, can generate redundant features in a feature map. To control the infinite expansion of feature maps, it is necessary to reject features that are misidentified, while also avoiding the removal of features that have tended to be stable but perform poorly for a short period of time.
In one embodiment of the present disclosure, it is necessary to remove feature points with identification errors from an updated feature map, calculate a ratio of the number of effective observations of each feature point in the updated feature map to the number of theoretical observations, and generate an effective observation rate of each feature point in the updated feature map. When the effective observation times of the feature points in the replaced feature map are smaller than a first preset threshold value and the effective observation rate is smaller than a second preset threshold value, the feature points are used as feature points to be removed, and the feature points are removed from the updated feature map. It should be noted that the first preset threshold may be set to 20, and the second preset threshold may be set to 0.5.
After generating the updated feature map, the method further comprises: if a first feature point exists in each feature point in the updated feature map, and the updated effective observation times are larger than or equal to a first preset threshold value, updating the first feature point from an untrusted landmark to a trusted landmark.
After eliminating the feature points with the identification errors, if a first feature point exists in the updated feature map, updating the first feature point from an untrusted landmark to a trusted landmark and setting a matchable mark to be 1 when the effective observation times of the first feature point are greater than or equal to a first preset threshold. That is, observations of the feature are deemed to be reliable enough to be used as a trusted landmark for subsequent positioning algorithms.
According to the technical scheme, the inherent attribute is defined for each feature to initialize the feature map, the feature points in the current feature point set are divided into the matchable feature and the new feature through matching of the current feature point set and the initialized feature map, a Kalman filter is independently established for the matchable feature and the new feature, updating of each feature is tracked, evaluation and rejection are carried out according to the historical observation effect of the feature, calculation memory is saved, stability of the feature map is greatly improved, map construction quality of a robot is guaranteed, and positioning and obstacle avoidance capability is improved.
The embodiment of the present disclosure also provides another method for updating a feature map of a mobile robot, and fig. 2 is a schematic flow chart of another method for updating a feature map of a mobile robot provided in the embodiment of the present disclosure, which mainly includes three parts, namely, initializing a feature map, updating a feature map, evaluating features, and rejecting features. As shown in fig. 2, the overall flowchart is first determined whether the feature map has been defined by initialization, and if not, the feature map is initialized. If the feature map has been defined by initialization, traversing each feature point in the current feature point set, and performing the following operations: and taking out one feature point in the current feature point set, and performing nearest neighbor matching with the feature point in the initialized feature map. Judging whether the feature point is a new feature point according to the matching result, if the feature point matched with the feature point exists in the initialized feature map, indicating that the feature point is not the new feature point, carrying out Kalman updating on the feature of the feature point, judging whether the feature requirement of the trusted landmark is met, and if so, marking the trusted landmark. If the feature points matched with the feature points do not exist in the initialized feature map, expanding the feature points into new features. And traversing all the characteristic points in the current characteristic point set according to the method, removing low-quality characteristics after traversing, and generating an updated characteristic map.
The method comprises the following specific processes of initializing a feature map, updating the feature map, evaluating and rejecting the features, wherein the specific processes of the three parts are as follows: firstly, initializing a feature map, and defining S k For the characteristic map at time k, C k Extracting characteristic point sets obtained by characteristics for the current point cloud, and when a characteristic map does not exist, using a first frame point cloud characteristic point set pair S k Initialization is performed. The initialization is to initially define the inherent attribute of each feature, and the attribute of a certain feature not only indicates the difference between the attribute and other features, but also includes the change trend and the expression of the attribute in multiple historical observations, and in this embodiment, 6 attributes are defined for a single feature, which are respectively as follows:
(1) Types. The feature types are divided into circular arcs and angular points, and the two features are distinguished during updating and matching, so that the operation efficiency can be greatly improved.
(2) Global coordinates. The global position of the current feature point of a certain feature is recorded, the global position is also the current state quantity of the feature, the coordinates are used for subsequent updating and as map matching features, the feature parameterization expression is embodied, and the feature point coordinates are updated all the time along with the accumulation of multiple observations of the certain feature.
(3) Number of theoretical observations N A . If a feature is within the range of lidar detection, it should be theoreticallySuccessful detection of N A The value is incremented by one.
(4) Number of effective observations N V . Every time a feature is successfully associated with a feature point in the new feature point set, it proves that the feature point is successfully observed in the laser scanning, and N is the same as that of the feature point V The value is incremented by one.
(5) Effective observation rate r V . In the actual observation process, the shielding of other obstacles and the failure of the observation sample points are not required to cause the observation failure of a certain theoretical observable feature, r V Can be used to represent the effective degree of observation of a feature, which is calculated as follows:
(6) The tag T may be matched. It is determined whether the feature can act as a marker of a trusted landmark, with a value of "0" or "1".
All feature points in the first feature point set are respectively used as independent features to record the type and global coordinates of the feature points, and N is respectively used as the independent features A 、N V R V All are set to be 1 and 0, and the feature map is initialized.
And secondly, updating the feature map. Defining global coordinates of a feature as state quantityThe upper and lower marks respectively represent the characteristic sequence number and the moment, and the Kalman filter motion and observation model are set as follows:
in the method, in the process of the invention,for a new observed quantity of a certain feature, only static features are observed in this embodiment, so that the features are considered to be static, the observed quantity is consistent with the expression of the state quantity, and the state transition matrix F B And an observation matrix H B Are all unit matrixes, w B And v B Respectively representing process noise and observation noise which are zero-mean Gaussian white noise and are independent of each other, and the characteristic observation quality is commonly influenced by laser radar error, characteristic fitting error and positioning error, so that Q B And R is B Can be obtained by multiple experimental adjustment.
The filtering model analysis shows that the state quantity can be updated when a certain characteristic is obtained from new observation. The feature points in the current feature point set are taken out one by one and are matched with the feature state quantity in the feature map in a nearest neighbor way, namely, the feature points and the state quantity with the nearest distance in the feature map form a point pair, and the distance between two points in the point pair is defined as d match The conditions for successful two-point matching are determined as follows:
d match ＜0.1m
after successful matching of the set point pair, the set point pair is regarded as a valid observation, and the characteristic N V The value is added by one, the feature point is used as a new observed quantity to update the corresponding state quantity, and the Kalman filter updating formula of the single feature is as follows:
in the method, in the process of the invention,and->A priori estimated state quantity and a priori estimated covariance matrix, respectively,)>Know->The posterior estimated covariance matrix and the kalman gain are represented, respectively. Through the Kalman filtering process, as the observation of a certain feature is gradually accumulated, the covariance matrix is continuously converged, and the state quantity tends to be stable.
In the feature map updating process, N is used A 、N V R V Three parameters evaluate the historical observation performance of a certain feature, and the observation effect of some features may be very poor in the mobile robot mapping process, for the following reasons:
(1) The feature is detected from dynamic obstacles;
(2) This feature is obscured by other obstructions;
(3) Other special situations such as sudden increase of laser radar error, wrong feature identification, disorder of robot positioning and the like can generate redundant features in the feature map, and three parameter values of the features are very low.
To control the infinite expansion of the feature map, it is necessary to eliminate the feature of the recognition error while avoiding the removal of the feature that has tended to be stable but performs poorly in a short time, and to integrate the above analysis, the following conditions are set:
if a feature meets the two conditions, the feature is removed from the feature map. When a certain feature satisfies the following condition:
N V ≥20
i.e., the observation of the feature is deemed to be reliable enough to be used as a trusted landmark for subsequent positioning algorithms, which may match the flag tset "1".
The embodiment of the present disclosure further provides a device for updating a feature map of a mobile robot, and fig. 3 is a schematic structural diagram of the device for updating a feature map of a mobile robot provided in the embodiment of the present disclosure, as shown in fig. 3, where the device includes:
At least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to: acquiring point cloud data of the mobile robot at the current moment, and generating a current feature point set according to a plurality of feature points in the point cloud data, wherein the point cloud data comprises a plurality of feature points; carrying out nearest neighbor matching on a plurality of feature points in the current feature point set and feature points in a preset initialization feature map, wherein the preset initialization feature map is an initialization feature map corresponding to the last moment of the current moment; dividing a plurality of feature points in the current feature point set into a first type of feature points and a second type of feature points according to a matching result of nearest neighbor matching, wherein the feature points in the first type of feature points are respectively matched with the corresponding feature points in the initialized feature map, and the feature points in the second type of feature points are not matched with the feature points in the initialized feature map; updating the position information of the corresponding feature points matched with the first type of feature points in a preset initialization feature map according to the pre-acquired position information of the first type of feature points, and generating a first feature map; and adding each feature point in the second type of feature points to the first feature map according to the pre-acquired position information of the second type of feature points, and generating an updated feature map.
The present specification embodiments also provide a non-volatile computer storage medium storing computer-executable instructions configured to: acquiring point cloud data of the mobile robot at the current moment, and generating a current feature point set according to a plurality of feature points in the point cloud data, wherein the point cloud data comprises a plurality of feature points; carrying out nearest neighbor matching on a plurality of feature points in the current feature point set and feature points in a preset initialization feature map, wherein the preset initialization feature map is an initialization feature map corresponding to the last moment of the current moment; dividing a plurality of feature points in the current feature point set into a first type of feature points and a second type of feature points according to a matching result of nearest neighbor matching, wherein the feature points in the first type of feature points are respectively matched with the corresponding feature points in the initialized feature map, and the feature points in the second type of feature points are not matched with the feature points in the initialized feature map; updating the position information of the corresponding feature points matched with the first type of feature points in a preset initialization feature map according to the pre-acquired position information of the first type of feature points, and generating a first feature map; and adding each feature point in the second type of feature points to the first feature map according to the pre-acquired position information of the second type of feature points, and generating an updated feature map.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, devices, non-volatile computer storage medium embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the section of the method embodiments being relevant.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing is merely one or more embodiments of the present description and is not intended to limit the present description. Various modifications and alterations to one or more embodiments of this description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, or the like, which is within the spirit and principles of one or more embodiments of the present description, is intended to be included within the scope of the claims of the present description.
Claims (8)
1. A method for updating a feature map of a mobile robot, the method comprising:
acquiring point cloud data of a mobile robot at the current moment, and generating a current feature point set according to a plurality of feature points in the point cloud data, wherein the point cloud data comprises a plurality of feature points;
performing nearest neighbor matching on a plurality of feature points in the current feature point set and feature points in a preset initialization feature map, wherein the preset initialization feature map is an initialization feature map corresponding to the last time of the current time;
dividing a plurality of feature points in the current feature point set into a first type of feature points and a second type of feature points according to the matching result of the nearest neighbor matching, wherein the feature points in the first type of feature points are respectively matched with the corresponding feature points in the initialized feature map, and the feature points in the second type of feature points are not matched with the feature points in the initialized feature map;
updating the position information of the corresponding feature points matched with the first type of feature points in the preset initialization feature map according to the pre-acquired position information of the first type of feature points, so as to generate a first feature map;
According to the pre-acquired position information of the second type of feature points, adding each feature point in the second type of feature points into the first feature map, and generating an updated feature map;
before the plurality of feature points in the current feature point set are respectively matched with the feature points in the preset initialization feature map in the nearest neighbor mode, the method further comprises the following steps:
acquiring a plurality of characteristic points in point cloud data of the mobile robot at a moment previous to the current moment;
initializing and defining each feature point in the feature points to generate the initialized feature map;
the initializing and defining each feature point in the plurality of feature points specifically includes:
acquiring feature types of each feature point in the plurality of feature points, and defining the feature types of each feature point in the plurality of feature points according to the feature types of each feature point, wherein the feature types comprise arc types and corner types;
acquiring global position coordinates of each feature point in the plurality of feature points, and defining position information of each feature point according to the global position coordinates of each feature point;
Setting the theoretical observation times and the effective observation times of each of the plurality of feature points as initial values;
each feature point of the plurality of feature points is defined as an untrusted landmark.
2. The method for updating a feature map of a mobile robot according to claim 1, wherein the performing nearest neighbor matching on the plurality of feature points in the current feature point set with feature points in a preset initialized feature map respectively comprises:
acquiring position information of each feature point in the initialized feature map;
and carrying out nearest neighbor matching on the plurality of feature points in the current feature point set and the position information of each feature point in the initialized feature map one by one.
3. The method for updating a feature map of a mobile robot according to claim 1, wherein the step of classifying the plurality of feature points in the current feature point set into a first type of feature point and a second type of feature point according to the matching result of the nearest neighbor matching specifically comprises:
if a specified feature point exists in a plurality of feature points in the current feature point set, and the distance between the specified feature point and a corresponding feature point in the initialized feature map is smaller than a preset threshold, judging that the matching result of the nearest neighbor matching is successful, and taking the specified feature point as a first type feature point;
If a current feature point exists in the plurality of feature points in the current feature point set, and the distance between the current feature point and any one feature point in the initialized feature map is larger than or equal to a preset threshold value, judging that the matching result of the nearest neighbor matching is unsuccessful, and taking the current feature point as a second type feature point.
4. The method for updating a feature map of a mobile robot according to claim 1, wherein updating, in the preset initialization feature map, the location information of the corresponding feature point matched with the first type feature point according to the pre-acquired location information of the first type feature point, to generate a first feature map, specifically includes:
acquiring the position information of each feature point in the first type of feature points as first position information;
acquiring position information of each current feature point matched with each feature point in the first type of feature points in the preset initialization feature map as second position information;
updating the position information of each current feature point according to the first position information and the second position information, and generating the position information of each current feature point so as to update the position information of each current feature point;
And setting the effective observation times of each current feature point matched with each feature point in the first type feature points in the preset initialization feature map to be an initial value plus one so as to update the effective observation times and generate updated effective observation times of each current feature point.
5. The method for updating a feature map of a mobile robot according to claim 4, wherein after the generating the updated feature map, the method further comprises:
generating an effective observation rate of each feature point in the updated feature map according to the ratio of the effective observation times to the theoretical observation times of each feature point in the updated feature map;
judging whether feature points to be removed exist in the feature points in the updated feature map or not according to the effective observation times of the feature points in the updated feature map and the effective observation rate of the feature points in the updated feature map, wherein the effective observation times of the feature points to be removed after updating are smaller than a first preset threshold value, and the effective observation rate is smaller than a second preset threshold value;
And when the feature points to be removed exist in the updated feature map, removing the feature points to be removed from the updated feature map.
6. The method for updating a feature map of a mobile robot according to claim 4, wherein after the generating the updated feature map, the method further comprises:
if a first feature point exists in each feature point in the updated feature map, and the updated effective observation times are larger than or equal to a first preset threshold value, updating the first feature point from an untrusted landmark to a trusted landmark.
7. A feature map updating apparatus of a mobile robot, the apparatus comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring point cloud data of a mobile robot at the current moment, and generating a current feature point set according to a plurality of feature points in the point cloud data, wherein the point cloud data comprises a plurality of feature points;
Performing nearest neighbor matching on a plurality of feature points in the current feature point set and feature points in a preset initialization feature map, wherein the preset initialization feature map is an initialization feature map corresponding to the last time of the current time;
dividing a plurality of feature points in the current feature point set into a first type of feature points and a second type of feature points according to the matching result of the nearest neighbor matching, wherein the feature points in the first type of feature points are respectively matched with the corresponding feature points in the initialized feature map, and the feature points in the second type of feature points are not matched with the feature points in the initialized feature map;
updating the position information of the corresponding feature points matched with the first type of feature points in the preset initialization feature map according to the pre-acquired position information of the first type of feature points, so as to generate a first feature map;
according to the pre-acquired position information of the second type of feature points, adding each feature point in the second type of feature points into the first feature map, and generating an updated feature map;
Before the plurality of feature points in the current feature point set are respectively matched with the feature points in the preset initialization feature map in the nearest neighbor way, the method further comprises the following steps:
acquiring a plurality of characteristic points in point cloud data of the mobile robot at a moment previous to the current moment;
initializing and defining each feature point in the feature points to generate the initialized feature map;
the initializing and defining each feature point in the plurality of feature points specifically includes:
acquiring feature types of each feature point in the plurality of feature points, and defining the feature types of each feature point in the plurality of feature points according to the feature types of each feature point, wherein the feature types comprise arc types and corner types;
acquiring global position coordinates of each feature point in the plurality of feature points, and defining position information of each feature point according to the global position coordinates of each feature point;
setting the theoretical observation times and the effective observation times of each of the plurality of feature points as initial values;
each feature point of the plurality of feature points is defined as an untrusted landmark.
8. A non-transitory computer storage medium storing computer-executable instructions configured to:
acquiring point cloud data of a mobile robot at the current moment, and generating a current feature point set according to a plurality of feature points in the point cloud data, wherein the point cloud data comprises a plurality of feature points;
performing nearest neighbor matching on a plurality of feature points in the current feature point set and feature points in a preset initialization feature map, wherein the preset initialization feature map is an initialization feature map corresponding to the last time of the current time;
dividing a plurality of feature points in the current feature point set into a first type of feature points and a second type of feature points according to the matching result of the nearest neighbor matching, wherein the feature points in the first type of feature points are respectively matched with the corresponding feature points in the initialized feature map, and the feature points in the second type of feature points are not matched with the feature points in the initialized feature map;
updating the position information of the corresponding feature points matched with the first type of feature points in the preset initialization feature map according to the pre-acquired position information of the first type of feature points, so as to generate a first feature map;
According to the pre-acquired position information of the second type of feature points, adding each feature point in the second type of feature points into the first feature map, and generating an updated feature map;
before the plurality of feature points in the current feature point set are respectively matched with the feature points in the preset initialization feature map in the nearest neighbor way, the method further comprises the following steps:
acquiring a plurality of characteristic points in point cloud data of the mobile robot at a moment previous to the current moment;
initializing and defining each feature point in the feature points to generate the initialized feature map;
the initializing and defining each feature point in the plurality of feature points specifically includes:
acquiring feature types of each feature point in the plurality of feature points, and defining the feature types of each feature point in the plurality of feature points according to the feature types of each feature point, wherein the feature types comprise arc types and corner types;
acquiring global position coordinates of each feature point in the plurality of feature points, and defining position information of each feature point according to the global position coordinates of each feature point;
Setting the theoretical observation times and the effective observation times of each of the plurality of feature points as initial values;
each feature point of the plurality of feature points is defined as an untrusted landmark.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210236656.8A CN114577215B (en) | 2022-03-10 | 2022-03-10 | Method, equipment and medium for updating characteristic map of mobile robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210236656.8A CN114577215B (en) | 2022-03-10 | 2022-03-10 | Method, equipment and medium for updating characteristic map of mobile robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114577215A CN114577215A (en) | 2022-06-03 |
| CN114577215B true CN114577215B (en) | 2023-10-27 |
Family
ID=81780387
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210236656.8A Active CN114577215B (en) | 2022-03-10 | 2022-03-10 | Method, equipment and medium for updating characteristic map of mobile robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114577215B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101000507A (en) * | 2006-09-29 | 2007-07-18 | 浙江大学 | Method for moving robot simultanously positioning and map structuring at unknown environment |
| CN103268729A (en) * | 2013-05-22 | 2013-08-28 | 北京工业大学 | Mobile robot cascading type map creating method based on mixed characteristics |
| CN104537709A (en) * | 2014-12-15 | 2015-04-22 | 西北工业大学 | Real-time three-dimensional reconstruction key frame determination method based on position and orientation changes |
| CN107491071A (en) * | 2017-09-04 | 2017-12-19 | 中山大学 | A kind of Intelligent multi-robot collaboration mapping system and its method |
| CN108917761A (en) * | 2018-05-07 | 2018-11-30 | 西安交通大学 | A kind of accurate positioning method of unmanned vehicle in underground garage |
| CN111351493A (en) * | 2018-12-24 | 2020-06-30 | 上海欧菲智能车联科技有限公司 | Positioning method and system |
| CN111780763A (en) * | 2020-06-30 | 2020-10-16 | 杭州海康机器人技术有限公司 | Visual positioning method and device based on visual map |
| CN113701739A (en) * | 2020-05-22 | 2021-11-26 | 杭州海康机器人技术有限公司 | Map updating method and device |
| CN114092898A (en) * | 2020-07-31 | 2022-02-25 | 华为技术有限公司 | Target object sensing method and device |
| CN114114316A (en) * | 2021-10-19 | 2022-03-01 | 山东新一代信息产业技术研究院有限公司 | Method for efficiently and accurately identifying arc features |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108732584B (en) * | 2017-04-17 | 2020-06-30 | 百度在线网络技术（北京）有限公司 | Method and device for updating map |
| CN109579847B (en) * | 2018-12-13 | 2022-08-16 | 歌尔股份有限公司 | Method and device for extracting key frame in synchronous positioning and map construction and intelligent equipment |
-
2022
- 2022-03-10 CN CN202210236656.8A patent/CN114577215B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101000507A (en) * | 2006-09-29 | 2007-07-18 | 浙江大学 | Method for moving robot simultanously positioning and map structuring at unknown environment |
| CN103268729A (en) * | 2013-05-22 | 2013-08-28 | 北京工业大学 | Mobile robot cascading type map creating method based on mixed characteristics |
| CN104537709A (en) * | 2014-12-15 | 2015-04-22 | 西北工业大学 | Real-time three-dimensional reconstruction key frame determination method based on position and orientation changes |
| CN107491071A (en) * | 2017-09-04 | 2017-12-19 | 中山大学 | A kind of Intelligent multi-robot collaboration mapping system and its method |
| CN108917761A (en) * | 2018-05-07 | 2018-11-30 | 西安交通大学 | A kind of accurate positioning method of unmanned vehicle in underground garage |
| CN111351493A (en) * | 2018-12-24 | 2020-06-30 | 上海欧菲智能车联科技有限公司 | Positioning method and system |
| CN113701739A (en) * | 2020-05-22 | 2021-11-26 | 杭州海康机器人技术有限公司 | Map updating method and device |
| CN111780763A (en) * | 2020-06-30 | 2020-10-16 | 杭州海康机器人技术有限公司 | Visual positioning method and device based on visual map |
| WO2022002039A1 (en) * | 2020-06-30 | 2022-01-06 | 杭州海康机器人技术有限公司 | Visual positioning method and device based on visual map |
| CN114092898A (en) * | 2020-07-31 | 2022-02-25 | 华为技术有限公司 | Target object sensing method and device |
| CN114114316A (en) * | 2021-10-19 | 2022-03-01 | 山东新一代信息产业技术研究院有限公司 | Method for efficiently and accurately identifying arc features |
Non-Patent Citations (4)
| Title |
|---|
| 3D simultaneous localization and mapping for mobile robot based on VSLAM;Lin Huican et al.;Journal of Computer Applications;第37卷(第10期);全文 * |
| 一种改进的RRT路径规划算法;宋金泽等;电子学报;第38卷(第2A期);全文 * |
| 一种自适应特征地图匹配的改进VSLAM算法;张峻宁等;自动化学报;第45卷(第3期);全文 * |
| 基于ORB关键帧匹配算法的机器人SLAM实现;艾青林;余杰;胡克用;陈琦;;机电工程(05);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114577215A (en) | 2022-06-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11709058B2 (en) | Path planning method and device and mobile device | |
| US10748061B2 (en) | Simultaneous localization and mapping with reinforcement learning | |
| Kwok et al. | An efficient multiple hypothesis filter for bearing-only SLAM | |
| US8649557B2 (en) | Method of mobile platform detecting and tracking dynamic objects and computer-readable medium thereof | |
| JP6773471B2 (en) | Autonomous mobile and environmental map updater | |
| CN107607107B (en) | Slam method and device based on prior information | |
| CN110749901B (en) | Autonomous mobile robot, map splicing method and device thereof, and readable storage medium | |
| CN111609852A (en) | Semantic map construction method, sweeping robot and electronic equipment | |
| CN112880694B (en) | Method for determining the position of a vehicle | |
| JP5776332B2 (en) | Map processing method and program, and robot system | |
| CN111578958A (en) | Mobile robot navigation real-time positioning method, system, medium and electronic device | |
| CN110900602A (en) | Positioning recovery method and device, robot and storage medium | |
| CN111354022A (en) | Target tracking method and system based on kernel correlation filtering | |
| CN110736456A (en) | Two-dimensional laser real-time positioning method based on feature extraction in sparse environment | |
| Stachniss et al. | Analyzing gaussian proposal distributions for mapping with rao-blackwellized particle filters | |
| Demim et al. | Simultaneous localisation and mapping for autonomous underwater vehicle using a combined smooth variable structure filter and extended kalman filter | |
| CN110335282B (en) | Contour line segment feature extraction method based on grids | |
| CN114577215B (en) | Method, equipment and medium for updating characteristic map of mobile robot | |
| CN116563341A (en) | Visual positioning and mapping method for processing dynamic object in complex environment | |
| WO2023072269A1 (en) | Object tracking | |
| Thallas et al. | Particle filter—Scan matching hybrid SLAM employing topological information | |
| US20230350422A1 (en) | Information processing apparatus, information processing method, and information processing program | |
| JP2016177749A (en) | Mobile body control device, program, and integrated circuit | |
| CN113112565A (en) | Map construction method based on robot vision closed-loop detection algorithm, storage medium and equipment | |
| CN112683273A (en) | Adaptive incremental mapping method, system, computer equipment and storage medium |
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 |