Sie sind auf Seite 1von 8

Robotics and Autonomous Systems 59 (2011) 402–409

Contents lists available at ScienceDirect

Robotics and Autonomous Systems


journal homepage: www.elsevier.com/locate/robot

Prediction-based geometric feature extraction for 2D laser scanner


Yilu Zhao, Xiong Chen ∗
Intelligent Control Research Lab, Department of Electronic Engineering, Fudan University, Shanghai 200433, PR China

article info abstract


Article history: This paper presents a novel algorithm for detecting line and circle features from 2D laser range scans.
Received 16 April 2009 Unlike the conventional methods that use two stages for separating the features: data segmentation
Received in revised form and feature separation in each segment, the proposed algorithm adopts a new structure and thus the
17 January 2011
computation complexity is much reduced. Moreover, it does not depend on prior knowledge of the
Accepted 8 February 2011
Available online 19 February 2011
environment, and it requires a minimum number of points per segment. We utilize prediction to achieve
the above goals, so the algorithm is named prediction-based feature extraction (PFE). The efficiency and
Keywords:
accuracy of the method is demonstrated by the experiments results.
Feature extraction © 2011 Elsevier B.V. All rights reserved.
Mobile robotics
Line fitting
Circle fitting

1. Introduction The conventional feature extraction methods are divided


into three stages: (1) data segmentation/breakpoint detection,
One of the key problems of mobile robotics is the reliable (2) feature separation in each segment and (3) parameter
and accurate acquisition of the robot’s environmental information, calculation for each feature. Segmentation is the process to classify
which constitutes the foundation of the followed operations, such each scan data point into several groups, and each of them is
as navigation and SLAM [1–4]. Robots are usually equipped with associated to different surfaces of the environment. Breakpoints
sensors to gather the environment information, among which laser are the boundary of the segments, and are usually detected by
measurement system (LMS) is most widely used. The laser scans the distance between adjacent points. If the distance between
the environment by a fixed angle resolution and angle range. In them is larger than a threshold, they are considered breakpoints.
each scan the laser returns one frame of data points, and each data Obviously a constant threshold is not proper. Adaptive breakpoint
point represents the position of the obstacle in the direction of detector [5] adaptively calculates the threshold and is a relatively
the corresponding laser beam. Compared to other sensors, such as widely used choice for breakpoint detection. It defines a virtual line
sonar, laser measurement system has better precision and higher passing through the current scan point, representing an extreme
speed, which render it to be used widely in modern days. case when an environment line can be reliably detected. The
In order to increase the efficiency and robustness, it is needed virtual line forms a threshold circle along with the information of
that sensor data is transformed into a more compact form. Typical the scan direction. If the next scan point lies outside the circle,
choices for the environment representation include topological, it is considered a breakpoint. However, the method has some
cell-based and feature-based approaches. In this paper, we drawbacks. First, the worst case that a line can be reliably detected
adopt feature-based approach for the environment representation. has little to do with the judgment of breakpoints, no physical
This method utilizes several feature models to represent the proof is provided. Second, the virtual line is formed by experience,
environment, and the success of the approach depends on the thus prior knowledge of the environment is needed. It decreases
choice of primitive feature type. One proper way is to utilize the the accuracy of the method and renders it not convenient to be
natural occurring structures of typical environment to achieve an migrated in different environments.
ideal performance. In most indoor structured environment, the In feature separation stage, early efforts that focused on line
map can be represented by lines and arcs/circles, which become features can be achieved efficiently by split-and-merge [6–8]. If
our choices of primitive features. considering both line and circle features, the problem is more
complicated. The main difficulty is to detect the boundary of circle
and line segments, as the circle may be embedded in lines. To solve
∗ Corresponding author.
it, geometric attempt [9,10], Gauss–Newton optimization [11],
E-mail addresses: yilu.zhao.joey@gmail.com (Y. Zhao), Hough transform [12–14] and curvature function [15,16] etc. have
chenxiong@fudan.edu.cn, 10110720042@fudan.edu.cn (X. Chen). all been investigated. The result of the above procedure is clusters
0921-8890/$ – see front matter © 2011 Elsevier B.V. All rights reserved.
doi:10.1016/j.robot.2011.02.003
Y. Zhao, X. Chen / Robotics and Autonomous Systems 59 (2011) 402–409 403

of data points, whereas each cluster represents a line segment


or a circle. Based on the above discussion, we can see that the
conventional methods need two stages to separate each feature.
In the third stage, feature parameters are calculated through line
fitting or circle fitting for each cluster.
In this paper, we propose a new approach to extract geometric
features (lines and arcs/circles) from 2D laser range data for indoor
environment. The main contribution of this work is that it presents
a new feature extraction framework, which can separate each Fig. 1. Laser scan scheme.
feature in one stage, while the conventional attempts need two
stages to do feature separation, thus the computation complexity is scanning a planar wall. The red triangle denotes the laser scanner
much reduced. Moreover, no prior knowledge of the environment and the green lines are laser beams. Each beam returns a data
is needed, and it can cope with the noisy real environment well. point; and the returned points are sequential, denoted by (Pi | 1 ≤
It also requires a minimum number of points per segment. The i ≤ N ).
physical principle is deeply discussed in this paper. We utilize We can see that if the wall is continuous and ideally planar, the
prediction to achieve these goals, so the proposed algorithm is returned scan points will also lie in the same segment, and the wall
named prediction-based feature extraction (PFE). can be formed from these points. As two points can form a line,
This paper is organized as follow: Section 2 describes the if the wall is continuous and ideally planar, either two or several
acquisition and pre-processing of laser data. The PFE algorithm is points will form the same line, i.e. the wall.
shown in Section 3. Section 4 presents experimental results and On the other hand, the laser scanner emits laser beams by angle
Section 5 summarizes conclusion. and the angular resolution is already known, so for every scan point
we can get the emit angle of it. That is to say, we can get the
2. Laser data acquisition and pre-processing emitting radial of each point once we obtain the scan data.
Thus, assuming that the wall is continuous and ideally planar,
Range data provided by laser sensors is typically in polar
we can predict the position of each point by simulating the real
coordinates and can be denoted as
laser scanning procedure, as if we do not actually know the position
{(ri , φi )|i = 1, . . . , N } of each point. For point Pk , two lines are formed. One is the Line 1
formed by the preceding Np points (Pi | k − Np ≤ i ≤ k − 1), which
where ri is the measured distance of an obstacle to the sensor
simulates the real wall surface; the other is the corresponding
rotating axis at direction φi . The scan points are acquired by the
emitting laser radial Line 2. The cross point of these two lines is
laser range finder with a given angular resolution 1φ = φi − φi−1 . p
called Prediction Point for point Pk , denoted by Pk . This process
Each data frame contains N data points.
simulates the real laser scanning procedure. If the actual wall is
A laser sensor has an inherent systematic error, and thus laser
continuous and ideally planar, the corresponding scan point Pk
range reading is usually perturbed by this systematic noise εs . The p
will certainly lie in the same position with its prediction point Pk .
distance is also contaminated by a statistical error εr , which is
On the other hand, if they are not at the same position, i.e. the
usually assumed to follow a Gaussian distribution with zero mean
distance between them is large enough to be detected, it means
and variance σr2 . Thus, if rm is the measured obstacle distance and
a discontinuity or turning of the surface appears.
rt is the true obstacle distance, they are related by
Of course, in real environment walls are not ideally planar
rm = rt + εs (rm ) + εr . and will certainly have relief. To overcome it we use more than
two points (Np points) to fit the line that simulate the real wall.
Our laser scanner is a SICK LMS200 doing planar range scans
Least square method is a widely used line-fitting algorithm [18],
with the maximum measurement range under 8 m. According to
the data sheet of the sensor, in this case it has a systematic error and we utilize LS method to fit the line from these points, the
εs of ±15 mm and a statistical error with standard deviation σr of mathematical representation is introduced in Section 3.5. In the
5 mm. In order to correct the systematic error, we can take several real environment the scan point Pk will not lie in the very same
p
range scan values and calculate the corresponding rm − rt . The position with its prediction point Pk , even they are in the same
error can be approximated by a sixth-order polynomial which fits segment. Thus we need to set a threshold dm to determine. If the
p
rm − rt in the least-squares sense, and the polynomial is used to distance is larger than the threshold, i.e. D(Pk , Pk ) > dm , they are
compensate the systematic error [5]. After correction, the residual considered breakpoints or turning points. Function D(·) denotes
noise is compatible with the value provided by the sensor data Euclidean distance of the two points.
sheet. The above discussion takes line as the example. When it comes
When range scans are taken with the sensor in motion, they to circle, the process is also applicable. Experiments show that
may be deformed as a result of the important scan time, which point number Np = 3 can already achieve ideal performance. As a
is commonly defined as motion error. So motion correction part of three points is only a small piece, if the wall is circular, such
is necessary. There exist many motion correction methods, for a small part can already be approximated by a line segment. So the
instance, algorithms described in [17]. After the above procedures, prediction method is also applicable in environments that contain
systematic error and motion error are corrected, and we can then circular features. This is why we can treat line and arc/circle
perform feature extraction upon the pre-processed scan data. features simultaneously.
From the above discussion, we can see that to the proposed
3. Prediction-based feature extraction method there is no difference between discontinuity and turning
of the surface. So using this method we can separate each feature
3.1. Physical principle in only one stage, while conventional algorithms need two stages.
Thus the computation complexity is reduced, and the algorithm is
First we introduce the physical principle of the proposed more easily to implement. In the proposed method we do not need
algorithm. For convenience we use line-shape obstacle as the to distinguish discontinuity or turning points, and they are named
example at first. Fig. 1 shows the scheme that a laser range finder is Mark Point in the followed sections of this paper.
404 Y. Zhao, X. Chen / Robotics and Autonomous Systems 59 (2011) 402–409

existing between them. Fig. 4(a) and (b) show the results of
detecting the boundary points between different features, i.e. the
turning of the surface.
In Fig. 4(a), the corner of the surface has been detected; in
Fig. 4(b) an arc lies between two line segments, the two boundary
points are also found out through the proposed method.
Fig. 4(c) shows that scan points which are inside the arc can be
dealt with using prediction and it will not bring about any trouble.
The prediction point is not far away from the test point. The test
data is also shown in the figure. From the above figures we can
see that the prediction-based method can effectively detect the
discontinuity and turning of the obstacle surface.

3.3. Check step

Fig. 2. Test data. The proposed algorithm utilized the characteristic that the scan
data is sequential. So we can use the preceding scan points to
3.2. Mark point detection predict the position, as we assume that they are in the same
segment.
In this section we will describe the calculation of prediction As we use Np points to simulate the surface, from the above
point in detail as well as its application to detecting mark points. discussion we can know that if the test point is in the same segment
We use an example to illustrate it. Fig. 2 shows the test data with its previous Np points, it will not be considered a mark point.
which is intercepted from a scan data frame. For convenience it However, at the beginning of a segment, such as the second or
is a relevantly simple data piece. third point, there will be some points which belong to the previous
There are 20 points (blue dots) in the test data. Obviously they segment that participate in the calculation of its prediction point.
form two line segments. The sequence is from right to left. We The result is that these points are wrongly marked. More definitely,
select two test points and calculate their corresponding prediction in the beginning of each segment there may be Np − 1 points
points to illustrate the proposed algorithm. One is edge point P12 that are wrongly marked, following the boundary that has been
and the other one is P10 which lies inside the segment. correctly detected. Fig. 5(a) shows the situation. The red asterisks
As has described before, we use two lines to calculate the denote that they are considered mark points. As we set Np = 3,
prediction point, and use Line 1 and Line 2 to denote them. In two points are wrongly marked.
Fig. 3, Line 1 is formed by the preceding three points of the However, the mistake is easy to amend, as the situation comes
test point and Line 2 is the radial from the laser scanner (the regularly. After calculating and marking the whole scan data frame,
original point). Red dot denotes the test point and red circle if Np mark points appear in sequence, we need to have it checked.
denotes the prediction point. As we have obtained the scan data, Assuming the first mark point is Pj , the point cluster is Pj∼j+Np −1 .
mathematically calculating the emitting angle of the test point is The way is simply using these points to calculate the prediction
needless. We can get Line 2 by just linking the original point and point of the next point Pj+Np . If the next point is in the same
the test point, which is very easy to implement. segment with them, the latter Np − 1 points Pj+1∼j+Np −1 are
In Fig. 3(a), the calculated prediction point is far from the test remarked as ordinary points; otherwise no change will be made.
point P12 , so the test point is considered a mark point, and it Boundary points come in pairs, so once we detect a mark point,
corresponds to that it is the boundary of the rupture. In Fig. 3(b), the preceding point is also considered a mark point. Fig. 5(b)
the two points are almost at the same position, as the test point P10 shows the correct result after check step. As in the experiments
does lie in the segment. The difference of these two cases is easy we set Np = 3, the check step does not need much computation.
to point out. From the scheme we can see that the discontinuity in Besides, the way we used to check the mark points is also
the test data can be successfully detected by the proposed method. prediction, thus in programming the only important part of code is
Several features may coexist in the same segment. They may be calculating prediction point, which decreases the complexity of the
lines with lines, or lines with circles, and there is no discontinuity algorithm.

a b

Fig. 3. Calculating prediction points: (a) an edge point as the test point, (b) an in-segment point as the test point.
Y. Zhao, X. Chen / Robotics and Autonomous Systems 59 (2011) 402–409 405

a b

Fig. 4. (a) Detecting mark point between line segments. (b) Detecting mark point between line and arc. (c) Dealing with points that are inside the arc.

a b

Fig. 5. (a) The result after calculating each point. (b) Correct result after check step.

3.4. Algorithm process and analysis data contains N points and M features, the total computation time
of this frame is N + M, where each time one prediction point is
The main contribution of this paper is that it proposes a novel calculated. As in the experiments we use three points to form the
algorithm to detect the boundary of the features and split the surface, the calculation is very fast.
features directly. After the above procedure, each detected mark Second, the algorithm is based on the laser scan data only.
point is the start or end point of one segment. The features have That is to say, no prior knowledge of the environment is required,
already been separated. Compared to the traditional methods, the which is however indispensable to adaptive breakpoint detector.
proposed algorithm has several advantages. This characteristic is another advantage of the proposed algorithm
First, the prediction method detects features by finding out the and it makes the method very easy to migrate between various
change in surface between adjacent points. To this method the environments and laser scanners with no modification needed.
breakpoints and boundary points means no difference. So we can On the other hand, as we use three points to predict the position
merge the traditional two-step feature separation procedure into of the next point, for reliably detection the minimum number of
one stage, which is much easier to implement, the computation points in a segment is four. Compared to other methods, this is a
complexity is much reduced and easy to estimate. If one frame of relatively loose restriction.
406 Y. Zhao, X. Chen / Robotics and Autonomous Systems 59 (2011) 402–409

3.5. Feature type identification and parameter acquisition minimize the geometric distances from the circle to the data
points, and algebraic fit, which minimize various approximate
The scan data are segmented after the mark points are found (or ‘algebraic’) distances. Compared to geometric fit, algebraic fits
out and each segment presents a separate feature, which can be a usually run faster. It was shown in [20,19] that all the circle fits
line or an arc/circle. We need to identify the feature type of each have the same covariance matrix, to the leading order, in the small-
segment. noise limit.
Here we use a simple but efficient way to do it. First, for The parameters of the circle are (a, b, R), where (a, b) denotes
each segment a line is fitted from all the points that belong to the center, and R the radius of the circle. One can fit a circle by
the segment using LS method. In polar coordinates, a line can be minimizing the function
represented by −
F = (ri2 − R2 )2
x cos α + y sin α = ρ −
= (x2i + y2i − 2axi − 2byi + a2 + b2 − R2 )2 .
where α represents the angle between x-axis and the normal of
the line and ρ is the perpendicular distance from the origin to the Changing parameters B = −2a, C = −2b, D = a2 + b2 − R2 ,
line. According to [18], using LS method to fit a line with point set the function F is transformed to
{(ri , φi ) | i = 1, . . . , n}, we can get the line parameters as −
p
F = (zi + Bxi + Cyi + D)2
tan(2α) =
q where zi = x2i + y2i . The problem reduces to a system of linear
1 − equations (normal equations) with respect to B, C , D that can be
ρ= (ri cos(φi − α)) easily solved, and then one recovers the natural circle parameters
N i
(a, b, R).
where We take data points (xi , yi ) as noisy observations of true points
−− − (x̃i , ỹi ) with noise variance σ 2 , which in our system is the statistic
p= ri rj sin(φi + φj ) + (1 − n)ri2 sin 2φi
error σr2 of laser scanner. According to [19], the covariance matrix
i j >i i
−− − of circle parameters Θ is given by
q= ri rj cos(φi + φj ) + (1 − n)ri2 cos 2φi .
V [Θ ] = σ 2 (W T W )−1
i j >i i
v1
 
u1 1
di being the distance of each point to the fitted line, the average
. . .
distance of all the points in the segment is where W =  .
.
.
.
. and ui
.
= (xi − a)/R, vi = (yi − b)/R.
n un vn 1
1−
d= di .
n i=1
3.6. Setting the thresholds
If the segment is a line segment, the points should not be
far away from the fitted line and the average distance d will be The thresholds that need to be set in the proposed method are
relatively small. But if the segment forms an arc/circle, the average two thresholds: dm , the threshold to detect mark points, and df , the
distance will be sufficiently large to be distinguished from the threshold to identify feature types.
previous case. Thus we can set a threshold df to compare. If d ≤ df , Investigating the distributing characteristic of laser scan data,
we take this segment as a line feature, otherwise the segment is we can see that it is affected by two factors: (1) the distance
treated as a circle feature. from laser to obstacle and (2) the angle between laser beam
For line features, the line parameters (ρ, α) have already been and obstacle surface. When the obstacle is near the laser, the
calculated during identification procedure. If we consider each data returned data points are concentrated. If the distance gets longer,
point to have the same Cartesian uncertainty, converting the points the data points become loose, i.e. the distance between adjacent
from polar coordinates (ri , φi ) to Cartesian coordinates (xi , yi ), points gets longer. When the acquired data is far from the laser
according to [18] the uncertainty of the line parameters can be range finder, the measurement uncertainty also gets higher. On
calculated by the other hand, the smaller the angle between laser beam and
obstacle surface, the longer the distance between adjacent points.
σρ2 = A The above phenomenon is caused by the fan-shaped measuring
σyy
2
cos2 χ + σxx
2
sin2 χ − 2σxy
2
sin χ cos χ mechanism of laser range finder. Thus, when setting the threshold
σα2 = A + d2 dm , we take into account above distance and angle factors. It can be
N
calculated by the following equation
where
π −ϕ
 
d0 r
1 − 1 − dm = +
x= xi y= yi λ rmax π
N
− N −
a= (xi − x)2 b=2 (xi − x)(yi − y) where r denotes the measured distance of the current point with
− r ∈ (0, rmax ], and ϕ denotes the acute angle between Line 1 and
c= (yi − y)2 d = y sin χ + x cos χ Line 2 in radian with ϕ ∈ (0, π /2]. rmax is the maximum mea-
surement range of the laser scanner. d0 is the initial threshold with
 π aσyy
2
− bσxy2 + c σxx2
χ = α+ A= . d0 = 50 in experiments. λ is the normalization coefficient with
2 (a − c ) + b2 λ = 2. The distance unit is millimeter, which is identical to the
For circle features we need to calculate the center points and setting of the laser scanner.
radius of them. Fitting circle from noisy data points has been When determining the feature types, it is relatively easy to
widely discussed, Al-Sharadqah and Chernov give an extensive identify whether the feature is a line or not, and we use a fixed
review and error analysis of existing circle fitting algorithms threshold df = 20 with the unit millimeter. Experiment results
in [19]. The methods are divided into geometric fit, which show that it can correctly identify feature types.
Y. Zhao, X. Chen / Robotics and Autonomous Systems 59 (2011) 402–409 407

a b

Fig. 6. (a) Pioneer3AT robot equipped with SICK LMS200 laser scanner. (b) Office-like test environment at Fudan University.

Fig. 7. (a) Raw scan data. (b) Result of mark point detection. (c) Feature extraction result. (d) Zoomed view of the environment surface.

4. Experiments The typical raw scan data is shown in Fig. 7(a). The robot is at
coordinate (0, 0), and the scan direction is to the positive direction
4.1. Feature detection result of x-axis. The robot is denoted by a red triangle.
Fig. 7(b) shows the result of mark point detection. Red asterisks
The feature extraction system is implemented on a P3AT robot denote mark points. The feature types are also identified. Arcs are
equipped with a SICK LMS200 sensor. The laser is configured with represented by green dots and line segments are in blue. From
180° scene, 0.5° resolution, so each scan frame is consisted of 360 the figure we can see that the lines and arcs have been correctly
data points. The unit of data is millimeter. Fig. 6(a) shows the robot
detected, including one arc that is embedded in lines. There are
used in the experiment.
several isolated mark points in the figure. They do not belong to
The experiments are taken in the Physics Building of Fudan
any segment and are ignored in the followed process, and this will
University. The test area is typical indoor office-like environment
and is composed of regular planar walls and circular pillars. not affect the final result. Fig. 7(c) shows the feature extraction
Fig. 6(b) shows the test environment. result, including two circles and several line segments. The squares
In our experiments, when taking laser reading, the robot denote boundaries of the line segments. Fig. 7(d) is the zoomed
remains stationary. If range scans are taken with the sensor in view of one of the arcs. We can see that the wall is uneven. The
motion, motion correction can be done by the introduction in algorithm successfully inhibited the noise and its robustness is
Section 2. The experiment results are shown in Figs. 7 and 8. visually demonstrated.
408 Y. Zhao, X. Chen / Robotics and Autonomous Systems 59 (2011) 402–409

Fig. 8. (a), (b) One frame of raw scan data and its feature extraction result. (c), (d) Another frame of raw scan data and its feature extraction result. (e), (f) Another test scan
data and its feature extraction result.

Fig. 8 is another two groups of experiments. In Fig. 8(a), data from these maps. The algorithms are programmed in C++ and
there exist four circles in the figure, with two separated and two performed on a Pentium4 2.4G PC.
embedded in the wall. Fig. 8(b) is the feature extraction result of To compare the speed and correctness of the algorithms, we
this data frame, and the features have been correctly extracted. experimented in three aspects: (1) execution time, (2) correct mark
Fig. 8(c) shows another frame of raw scan data. To demonstrate the of each point and (3) correct type identification of each feature.
method’s ability to be used in environments which contain many Correct mark of each point is verified by:
short features, we add some small boxes into the test environment. NumberFalseMarked
Thus we can see there are many small clusters of points in the raw FalseMarkRatio = ,
TotalPointNumber
data. Fig. 8(d) shows the feature extraction result of this data frame,
and the shortest line segment in this data frame contains four where NumberFalseMarked denotes the number of points that are
points. From the figure we can see that the features are correctly wrongly marked, including normal points that are marked as mark
extracted, including two circle features. point, and mark points that are omitted.
Correct type identification of each feature is obtained by:

4.2. Comparative study NumberFalseIdened


FalseIdenRatio = ,
TotalFeatureNumber
To give an indication of the speed and correctness of the where NumberFalseIdened denotes the number of features that
proposed algorithm, we have compared our method with some are wrongly identified, including circle marked as line, and line
existing methods that are commonly used in mobile robotics. In the marked as circle. The segments that contain less than four points
work proposed by Nunez et al. [15], adaptive breakpoint detector are considered bad features and are omitted. They are not included
by Borges and Aldon [5] is utilized to detect the breakpoints, and in total feature number.
the feature extraction is based on adaptive curvature function We performed 100 real/simulated scans and averagely one data
(ACF). In [15] the work has been compared with several other frame contains twelve features. The experiment result is shown in
works, the result shows that the work has several advantages. Thus Table 1.
it is suitable to be chosen as the comparing counterpart. From the table we can see that the proposed method is
We implemented the above mentioned algorithm, the param- significantly faster than ACF in average execution time. It is because
eters are chosen according to [15]. The use of the two methods is the compact structure of the proposed algorithm, which renders it
restricted to the segmentation of scan data and the identification superior in computation complexity to the conventional methods.
of line and circle features. To get enough experiment scan data, we In terms of correctness, the proposed method is more correct
also used Mapper3 to create several artificial maps as a supple- than ACF. However, no doubt the false detection rates of both the
ment. MobileSim is used to simulate the robot and get laser scan algorithms are considered to be low. The difference lies in that
Y. Zhao, X. Chen / Robotics and Autonomous Systems 59 (2011) 402–409 409

Table 1 [5] G.A. Borges, M. Aldon, Line extraction in 2D range images for mobile robotics,
Experiment results of the comparison. Journal of Intelligent and Robotic Systems 40 (2004) 267–297.
[6] V. Nguyen, S. Gächter, et al., A comparison of line extraction algorithms using
Proposed method ACF
2D range data for indoor mobile robotics, Autonomous Robots 23 (2007)
Average execution time (ms) 2.3 6.1 97–111.
False mark ratio 0.03 0.08 [7] T. Pavlidis, Steven L. Horowitz, Segmentation of plane curves, IEEE Transac-
False identification ratio 0.03 0.09 tions on Computers C-23 (8) (1974) 860–870.
[8] G.A. Borges, M.-J. Aldon, A split-and-merge segmentation algorithm for line
extraction in 2D range images, in: Proceedings of the International Conference
on Pattern Recognition, vol. 1, 2000, pp. 441–444.
methods based on curvature function need the segments to contain [9] J. Xavier, M. Pacheco, et al. Fast line, arc/circle and leg detection from laser
enough data points to form an identifiable characteristic. Thus if scan data in a player driver, in: Proceedings of the 2005 IEEE International
the environment contains many short features that are composed Conference on Robotics and Automation, April 2005, pp. 3930–3935.
[10] J. Vandorpe, H. Van Brussel, et al. Exact dynamic map building for a mobile
of relatively small pieces of data points, the false identification ratio robot using geometrical primitives produced by a 2D range finder, in:
will significantly increase, and such environment is quite common. Proceedings of the 1996 IEEE International Conference on Robotics and
In [15] we can see that the minimum number of points per segment Automation, vol. 1, April 1996, pp. 901–908.
[11] Sen Zhang, Lihua Xie, et al., Feature extraction for outdoor mobile robot
has been fixed to ten. This is a disadvantage of the methods based
navigation based on a modified Gauss–Newton optimization approach,
on curvature function. However, it has much reduced influence Robotics and Autonomous Systems 54 (2006) 277–287.
on PFE. As in experiments we use three points to predict the [12] R.O. Duda, P.E. Hart, Use of the hough transform to detect lines and curves in
position, for reliably detection the minimum number of points in a pictures, Communications of the ACM 15 (1) (1972) 11–15.
[13] J. Ryde, Huosheng Hu, Fast circular landmark detection for cooperative
segment is four. This renders the algorithm more adaptive to real localisation and mapping, in: Proceedings of the 2005 IEEE International
environments. Conference on Robotics and Automation, April 2005, pp. 2745–2750.
[14] Zhen Song, YangQuan Chen, et al. Some sensing and perception techniques
for an omnidirectional ground vehicle with a laser scanner, in: Proceedings
5. Conclusion of the 2002 IEEE International Symposium on Intelligent Control, 2002,
pp. 690–695.
In this paper a new algorithm for feature extraction from laser [15] P. Núñez, R. Vázquez-Martín, et al., Natural landmark extraction for mobile
robot navigation based on an adaptive curvature estimation, Robotics and
scan data is proposed. The main contribution is that it introduces Autonomous Systems 56 (2008) 247–264.
a new feature separation structure, which utilizes prediction to [16] R. Madhavan, H.F. Durrant-Whyte, Natural landmark-based autonomous
detect the mark points. Compared to the conventional methods, vehicle navigation, Robotics and Autonomous Systems 46 (2004) 79–95.
[17] Kai O. Arras, Nicola Tomatis, et al., Multisensor on-the-fly localization:
the time cost and computation complexity is much reduced. The precision and reliability for applications, Robotics and Autonomous Systems
method is based on laser data and no prior knowledge of the 34 (2001) 131–143.
environment is needed. It also has a minimal number of points [18] P. Jensfelt, H.I. Christensen, Pose tracking using laser scanning and minimalis-
tic environmental models, IEEE Transactions on Robotics and Automation 17
per segment, so it is much more adaptive to various different
(2) (2001) 138–147.
environments than other methods. The speed and accuracy of the [19] Ali Al-Sharadqah, Nikolai Chernov, Error analysis for circle fitting algorithms,
proposed method is demonstrated in experiments. Electronic Journal of Statistics 3 (2009) 886–911.
The proposed method can be applied to any application that [20] Prasanna Rangarajan, Kenichi Kanatani, Improved algebraic methods for circle
fitting, Electronic Journal of Statistics 3 (2009) 1075–1082.
needs line and/or circle feature extraction using laser scanner.
Furthermore, the proposed method can also be utilized in
laser data segmentation task by simply omitting the feature Yilu Zhao was born in China in 1986. He received the
type identification and parameter acquisition part. The above B.S. degree and M.S. Degree in electronic engineering
from Fudan University, Shanghai, China in 2007 and 2010,
applications are often seen for robots in unknown environment.
respectively. Now he is working toward the Ph.D. Degree
For example, the proposed method can be applied to small- from Fudan University at 2013. His research interests
sized robots such as cleaning robots and security robots, since include feature extraction, SLAM, and robot exploration.
the method is fast and compact. Our future work will focus on
integrating the proposed system with real time SLAM and target
tracking process.

References Xiong Chen was born in China in 1964. He received post-


Doctorate in Automatic Control from Tongji University,
[1] H. Durrant-Whyte, T. Bailey, Simultaneous localization and mapping: part I, Shanghai, China, in 1999. He is currently an Associate
IEEE Robotics & Automation Magazine 13 (2) (2006) 99–110. Professor in the Department of Electronic Engineering,
[2] T. Bailey, H. Durrant-Whyte, Simultaneous localization and mapping (SLAM): Fudan University, Shanghai, China and is a member of IEEE.
part II, IEEE Robotics & Automation Magazine 13 (3) (2006) 108–117. His research interests include automatic control, robot
[3] G.C. Anousaki, K.J. Kyriakopoulos, Simultaneous localization and map building path planning, SLAM and sensor network.
of skid-steered robots, IEEE Robotics & Automation Magazine 14 (1) (2007)
79–89.
[4] D.J. Spero, R.A. Jarvis, A Review of Robotic SLAM, Technical Report, Monash
University, MECSE-4-2007.

Das könnte Ihnen auch gefallen