Вы находитесь на странице: 1из 6

Research Proposal

Motivation

Localization and Mapping is the most important and fundamental problem in developing Cyber
Phisical sytems like Robotics. The idea of simultaneously finding the pose of the device (Localization) and extracting the features of the unknown environment (Mapping), gave a breakthrough in
1995 and became an eyeopener in 2005, when Stanley autonomous car won DARPA grand challenge, which actually included Simultaneous Localization and Mapping (SLAM) system. The
solution to SLAM problem has been seen as a holy grail for the mobile robotics community as it
would provide the means to make a robot truly autonomous. SLAM algorithms are employed in unmanned aerial vehicles, autonomous underwater vehicles, planetary rovers, Industrial systems and
even inside the human body. Solving SLAM problem efficiently demands robust solutions to Data
Association, Feature extraction and Convergence related problems. Addressing these problems
to dynamically changing environments make the SLAM prolem more challenging and interesting.
Moreover best possible Data Fusion techniques are to be developed, as multi-robot deployment has
become a recent fashion to share computations and hence reducing time complexity. Interestingly
Optimization based approaches can provide more accurate solutions to SLAM problem and hence
making possible to develop interesting applications such as, Perpetual life assistants for older or
disabled people, Autonomous Vacuum Cleaner, The distributed autonomous gardening system,
Self-driving Cars and many more.

Introduction

Robotic navigation, particularly when an external location reference such as a global positioning
system (GPS) is not available (eg: Indoor locations), requires the robot to be able to build a map
of the unknown environment in real-time and simultaneously work out its own location within the
map. Robust solutions to the Simultaneous Localization and Mapping (SLAM) problem, therefore,
underpins successful robot deployment in many application. The essential problem in SLAM is to
estimate robot location and the map of the environment, typically represented by a set of geometric
features, as measurements are gathered from a sensor as the robot moves through the environment.
The important point to note is, there is no single best solution to SLAM problem [1]. The method
chosen depends on number of factors.

2.1

Taxonomy of SLAM problem

Most important research papers identify the type of problems addressed by making the underlying
assumptions explicit in the following factors,
(i) Static vs Dyanmic : Static SLAM algorithms assume that the environment does not change
over time. Dynamic methods allow for changes in the environment. The vast majority of the
literature on SLAM assumes static environments. Mapping unstructured largesclae dynamic environments reamins an open research problem.

(ii) Topological vs Metric : A topological map might be defined over a set of distinct places and
a set of qualitative relations between these places. Metric SLAM methods provide metric information between the relation of such places.
(iii) Known vs Unknown Correspondence : The correspondence problem is the problem of
relating the identity of sensed things to other sensed things. The algorithms that do not make
assumptions (i.e correspondence is known) provide special mechanisms for estimating the correspondence of measured features to previously observed landmarks in the map. The problem of
estimating the correspondence is known as the data association problem [2].
(iv) Single-Robot Versus Multirobot SLAM : Most SLAM problems are defined for a singlerobot platform, although recently the problem of multirobot exploration [3] has gained in popularity.
By fusing data collected by different robots we can gain more insights about the environment and
moreover the job of computations can be divided among them so that computation time is reduced.
(v) Online vs Offline SLAM : The algorithms for the offline SLAM problem are often batch,
that is, they process all data at the same time [4]. Online SLAM seeks to recover the present
robot location, instead of the entire path. Algorithms that address the online problem are usually
incremental and can process one data item at a time. In the literature such algorithms are typically
called filters.

Statement of SLAM problem and Related Issues

Consider a mobile robot moving through an environment taking relative observations of a number
of unknown landmarks using a sensor located on the robot. At a time instant k, the following
quantities are defined as shown in figure 1 :

Figure 1: simultaneous estimate of robot and landmarks

Figure 2: Map and robot trajectory from SAM

xk : the state vector describing the location and orientation of the vehicle.
uk : the control vector, applied at time k 1 to drive the vehicle to a state xk at time k.
mi : a vector describing the location of the ith landmark whose true location is assumed time
invariant.
zik : an observation taken from the vehicle of the location of the ith landmark at time k.

In addition the following sets are also defined :


X0:k = {x0 , x1 , . . . , xk } = {X0:k1 , xk } : the history of vehicle locations.
U0:k = {u1 , u2 , . . . , uk } = {U0:k1 , uk } : the history of control inputs.
m = {m1 , m2 , . . . , mn } : the set of all landmarks.
Z0:k = {z1 , z2 , . . . , zk } = {Z0:k1 , zk } : the set of all landmark observations.
Since the control inputs and landmarks observations are prone to noise, we formulate the problem in
probabilistic form that requires the probability distribution P (xk , m|Z0:k , U0:k , x0 ) to be computed
for all times k. This can be done in a standard two-step recursive (sequential) prediction (timeupdate) correction (measurement-update) form as shown below,
Prediction Update :
Z
P (xk , m|Z0:k1 , U0:k , x0 ) =

P (xk |xk1 , uk ) P (xk1 , m|Z0:k1 , U0:k1 , x0 ) dxk1

(1)

Correction Update :
P (xk , m|Z0:k , U0:k , x0 ) =

P (zk |xk , m) P (xk , m|Z0:k1 , U0:k , x0 )


P (zk |Z0:k1 , U0:k )

(2)

Solutions to the above probabilistic SLAM problem involve finding an appropriate representation
for both the observation model and motion model that allows efficient and consistent computation
of the prior and posterior distributions in (1) and (2). The three main paradigms from which a
huge number of recently published methods are derived are
First comes the traditional approach, i.e the Extended Kalman Filter (EKF) for representing
the robots best estimate [5].
Second one uses the fact that the SLAM can be viewed as a Sparse Graph of constraints, and
it applies nonlinear optimization [1] for recovering the map and the robots locations.
Finally Particle Filter which applies nonparametric density estimation and efficient factorization methods to the SLAM problem [5].

3.1

Sensor and Process Models

The sensor observation z(k) at time k is a function of robot pose X(k) and state of environment
m is given by
z (k) = h (X(k), m) + w(k)
(3)
where w(k) is the sensor observation noise at time k. Virtually all SLAM literature assumes process
models with additive noise of the form
X (k + 1) = f (X(k), u(k)) + v(k)

(4)

where u(k), v(k), X(k) are the control, process noise and robot pose at time k repectively. Theoretical problems posed when the noises are not zero-mean as well as practical solutions to this
problem, perhaps through use of external information such as known landmarks remain interesting
challenges.

3.2

Consistency and Computational Issues

A solution to a dynamic estimation problem is said to be consistent if the estimate is unbiased and
the estimated covariance matrix matches the real mean square error. Both the EKF and particle
filter based solutions to SLAM can produce inconsistent estimates. In recent years there has been
a growing interest on the SLAM consistency issue among the research community. Despite many
advances by [6] limitations, together with its quadratic computational complexity associated with
the presence of a dense covariance matrix of order (3 + 2n) (3 + 2n) where n is the number of
landmarks, makes it impractical to use EKF to solve large-scale SLAM problems [6]. Although
extended Information lter (EIF) based algorithms can overcome the computational issues to some
extent [7] the issue of inconsistency remained unresolved.

3.3

Convergence

On condition that observation model is avilable and the feature states are noise free and static,
feature location uncertainty will monotonically decrease during SLAM.A number of researchers
conrm this fact for both the linear case [2] and the nonlinear case [8] in their work on EKF based
SLAM algorithms. Acheiving convergence for dynamic environments is still a challenging task.

Research Focus

I intend to focus on Optimization based approaches for solving SLAM problem, as these approaches
can provide more accurate and consistent solutions. Example of such approach is Smoothing and
Mapping [9] which estimate the complete robot trajectory and the map as shown in figure 2. In
general SLAM problem is non-linear and non-convex with large search space. Most of the existing
optimization based SLAM algorithms are based on Gauss-Newton or Levenberg-Marquardt optimizers that requires an initial guess to the robot poses and the map. Recent research demonstrated
that use of Stochastic Gradient Descent, Tree based Network Optimizer algorithm makes SLAM
problem to achieve good convergence results eventhough it starts from a poor initial guess [10], on
condition that noise covariance matrix is spherical. SLAM for dynamic, complex and large scale
environments using vision as the sole external sensor i.e cameras, is also my focus of research, as
cameras have become popular sensors in the robotics community and take the advantage of being
cheap, lightweight, and energy efficient. This vision based or visual SLAM [11] [12] uses concepts
from Computer Vision and Machine Learning [13] and Optimization as well, so as to address the
problem of Data Association and develop Data Fusion techniques (for example we can extract depth
information by fusing two images.)[14]. Finally I intend to work on improvements in computational
efficiency by fromulating the SLAM problem as Nonnegative Linear Least Squares and employing
Dimensionality Reduction[15] and try to answer questions such as how to obtain a map with given
accuracy in minimum time, or how to maximize the coverage with a fixed time horizon and a
required map quality.

Applications

Autonomous Cars : Intel survey discovered that 44 percent of American respondents said they
would like to live in a driverless city. This shows the demand in the market to build resilient

Figure 3: Wireless Capsule Endoscopy

Figure 4: Vacuum cleaner


Figure 5: Walker Assistant

autonomous cars. Many researchers proved SLAM is a good substitute where ever GPS is
absent and more erroneous. Advancements in Optimization based approaches solves SLAM
problem more accurately, which is very much desired in safe navigation for autonomous cars.
Home Automation : Methods from Robotics (SLAM) and Machine Learning can be used to
increase household efficiency and extend device functionality. Interesting devices such as
Automatic Vacuum cleaner [16] in figure 4, Perpetual life assistant for old or disbles as shown
in figure 5, etc can be build.
Wireless Capsule Endoscopy : SLAM also try to enhance Intels vision towards Health and
Life Sciences, by building systems such as Body-SLAM, that finds applications inside human
body. For example WCE (see figure 3) offers painless investigation of the entire small intestine
of human body. To detect precise position of the intestinal disease we need to localize the
capsule in the unknown map of the intestine. Body SLAM [17] enhances the positioning
accuracy of WCE, as it takes the advantage of Data Fusion of image sequences captured by
the WCEs embedded camera and the RF signal emitted by the capsule.

References
[1] Bruno Siciliano, Oussama Khatib. Springer Handbook of Robotics. Springer science and business media, 20-May-2008 - Computers - 1611 pages.
[2] Dissanayake, M.W.M.G., Newman, P. ; Clark, S. ; Durrant-Whyte, H.F. ; Csorba, M.. A
solution to the simultaneous localization and map building (SLAM) problem. Robotics and
Automation, IEEE Transactions on (Volume:17 , Issue: 3 )Jun 2001.
[3] Fox, D., Seattle, WA Ko, J. ; Konolige, K. ; Limketkai, B. ; Schulz, D. ; Stewart, B.. Distributed
Multirobot Exploration and Mapping Proceedings of the IEEE (Volume:94 , Issue: 7 )July
2006.
[4] M Montemerlo, S Thrun, D Koller, B Wegbreit. FastSLAM: A factored solution to the simultaneous localization and mapping problem Proc. AAAI Nat. Conf. Artif. Intell., pp.593 -598
2002 .

[5] Durrant-Whyte H, Bailey, Tim. Simultaneous localization and mapping: part I. Robotics and
Automation Magazine, IEEE (Volume:13 , Issue: 2 )June 2006.
[6] T. Bailey and H. Durrant-Whyte, Simultanouse localization and mapping (SLAM): Part II.
IEEE Robotics and Automation Magazine, 13(3):108-117, 2006.
[7] S. Thrun, W. Burgard, and D. Fox, Probabilistic Robotics. The MIT Press, 2005.
[8] S. Huang, G. Dissanayake. Convergence and consistency analysis for Extended Kalman Filter
Based SLAM. IEEE Transactions on Robotics, 23(5):1036-1049, 2007.
[9] F. Dellaert and M. Kaess. Square root SAM: Simultaneous localization and mapping via square
root information smoothing. International Journal of Robotics Research, 25(12):1181-1203,
2006.
[10] Olson, E. (Comput. Sci. and Artificial Intelligence Lab, MIT, Cambridge), MA Leonard J.
; Teller Fast iterative alignment of pose graphs with poor initial estimates.Robotics and Automation, 2006. ICRA 2006.
[11] Se S, Lowe D.G. ; Little, Vision-based global localization and mapping for mobile
robots.Robotics, IEEE Transactions on (Volume:21 , Issue: 3 )June 2005.
[12] Seo-Yeon Hwang, Jae-Bok Song Monocular Vision-Based SLAM in Indoor Environment Using
Corner, Lamp, and Door Features From Upward-Looking Camera.Industrial Electronics, IEEE
Transactions on 28 January 2011.
[13] Casarrubias-Vargas H, Petrilli-Barcelo A. ; Bayro-Corrochano E. EKF-SLAM and Machine
Learning Techniques for Visual Robot Navigation.Pattern Recognition (ICPR), 2010 20th International Conference on 23-26 Aug. 2010.
[14] Hollinger G.A.,Yerramalli S., Distributed Data Fusion for Multirobot Search.Robotics, IEEE
Transactions on (Volume:31 , Issue: 1 )22 December 2014.
[15] Heng Wanga, Shoudong Huang, Dimensionality reduction for point feature SLAM problems
with spherical covariance matrices.Automatica Volume 51, January 2015, Pages 149157.
[16] WooYeon Jeong, Kyoung Mu Lee, CV-SLAM: a new ceiling vision-based SLAM technique.Intelligent Robots and Systems, 2005. (IROS 2005). 2005 IEEE/RSJ International Conference on 2-6 Aug. 2005.
[17] Guanqun Bao,
Body-SLAM,
091313/unrestricted/main.pdf.

https://www.wpi.edu/Pubs/ETD/Available/etd-042814-

Вам также может понравиться