SLAM

In this work, a study of several laser-based 2D Simultaneous Localization and Mapping (SLAM) techniques available in Robot Operating System (ROS) is conducted. All the approaches have been evaluated and compared in 2D simulations and real world experiments. In order to draw conclusions on the performance of the tested techniques, the experimental results were collected under the same conditions and a generalized performance metric based on the k-nearest neighbors concept was applied. Moreover, the CPU load of each technique is examined. This work provides insight on the weaknesses and strengths of each solution. Such analysis is fundamental to decide which solution to adopt according to the properties of the intended final application.

Building consistent models of objects and scenes from moving sensors is an important prerequisite for many recognition, manipulation, and navigation tasks. Our approach integrates color and depth measurements seamlessly in a multi-resolution map representation. We process image sequences from RGB-D cameras and consider their typical noise properties. In order to align the images, we register view-based maps efficiently on a CPU using multiresolution strategies. For simultaneous localization and mapping (SLAM), we determine the motion of the camera by registering maps of key views and optimize the trajectory in a probabilistic framework. We create object models and map indoor scenes using our SLAM approach which includes randomized loop closing to avoid drift. Camera motion relative to the acquired models is then tracked in real-time based on our registration method. We benchmark our method on publicly available RGB-D datasets, demonstrate accuracy, efficiency, and robustness of our method, and compare it with state-of-theart approaches. We also report on several successful public demonstrations where it was used in mobile manipulation tasks.

This paper describes a probabilistic bail-out condition for multihypothesis testing based on Bennett’s inequality.
We investigate the use of the test for increasing the speed of an
appearance-only SLAM system where locations are recognised
on the basis of their sensory appearance. The bail-out condition
yields speed increases between 25x-50x on real data, with only
slight degradation in accuracy. We demonstrate the system
performing real-time loop closure detection on a mobile robot
over multiple-kilometre paths in initially unknown outdoor
environment

Localisation and mapping are the key requirements in mobile robotics to accomplish navigation. Frequently laser scanners are used, but they are expensive and only provide 2D mapping capabilities. In this paper we investigate the suitability of the Xbox Kinect optical sensor for navigation and simultaneous localisation and mapping. We present a prototype which uses the Kinect to capture 3D point cloud data of the external environment. The data is used in a 3D SLAM to create 3D models of the environment and localise the robot in the environment. By projecting the 3D point cloud into a 2D plane, we then use the Kinect sensor data for a 2D SLAM algorithm. We compare the performance of Kinectbased 2D and 3D SLAM algorithm with traditional solutions and show that the use of the Kinect sensor is viable. However, its smaller field of view and depth range and the higher processing requirements for the resulting sensor data limit its range of applications in practice.

Localization and mapping has been a long standing area of research, both in neuroscience, to understand how mammals navigate their environment, as well as in robotics, to enable autonomous mobile robots. In this paper, we treat navigation as inferring actions that minimize (expected) variational free energy under a hierarchical generative model. We find that familiar concepts like perception, path integration, localization and mapping naturally emerge from this active inference formulation. Moreover, we show that this model is consistent with models of hippocampal functions, and can be implemented in silico on a real-world robot. Our experiments illustrate that a robot equipped with our hierarchical model is able to generate topologically consistent maps, and correct navigation behaviour is inferred when a goal location is provided to the system.

—This paper focuses on the integration of Inertial Measurement Unit (IMU) with two Real-Time Kinematic (RTK) Global Positioning System (GPS) units in an adaptive Kalman filter (KF) for driftless estimation of a vehicle's attitude and position in 3-dimension. The observability analysis reveals that i) integration of a single GPS with IMU does not constitute an observable system; ii) integration of two GPS units with IMU results in a locally observable system provided that the line connecting two GPS antennas is not parallel with the vector of the measured acceleration, i.e., the sum of inertial and gravitational accelerations. The later case makes it possible compensate the error in the estimated orientation due to gyro drift and its bias without needing additional instrument for absolute orientation measurements, e.g., magnetic compass. Moreover, in order to cope with the fact that GPS systems sometimes lose their signal and receive inaccurate position data, the self-tuning filter estimates the covariance matrix associated with the GPS measurement noise. This allows the KF to incorporate GPS measurements in the data fusion process heavily only when the information received by GPS becomes reliably available. Finally, test results obtained from a mobile robot moving across uneven terrain demonstrate driftless 3D pose estimation.

Micro aerial vehicles (MAV) pose a challenge in
designing sensory systems and algorithms due to their size and
weight constraints and limited computing power. We present
an efficient 3D multi-resolution map that we use to aggregate
measurements from a lightweight continuously rotating laser
scanner. We estimate the robot’s motion by means of visual
odometry and scan registration, aligning consecutive 3D scans
with an incrementally built map.
By using local multi-resolution, we gain computational efficiency
by having a high resolution in the near vicinity of
the robot and a lower resolution with increasing distance from
the robot, which correlates with the sensor’s characteristics in
relative distance accuracy and measurement density. Compared
to uniform grids, local multi-resolution leads to the use of fewer
grid cells without loosing information and consequently results
in lower computational costs. We efficiently and accurately
register new 3D scans with the map in order to estimate the
motion of the MAV and update the map in-flight.
In experiments, we demonstrate superior accuracy and
efficiency of our registration approach compared to state-of-theart
methods such as GICP. Our approach builds an accurate 3D
obstacle map and estimates the vehicle’s trajectory in real-time.

is essential to many applications, but so far, most implementation rely on a-priori information and pre-deployed infrastructures such as maps. We show how techniques from mobile robotics, namely simultaneous localization and mapping can be used to automatically generate both localization information and 2D environment maps using headmounted inertial and laser range sensors. We present an initial implementation and the results of a number of experiments conducted in an office environment with focus on map degradation caused by shape ambiguities in the environment such as corridors.

The problem of state estimation using primarily visual data has received a lot of attention in the last decade. Several open-source packages have appeared addressing the problem, each supported by impressive demonstrations. Applying any of these packages on a new dataset, however, has been proven extremely challenging. Suboptimal performance, loss of localization, and challenges in customization have not produced a clear winner. Several other research groups have presented superb performance without releasing the code, sometimes materializing as commercial products. In this paper, ten of the most promising open-source packages are evaluated, by cross-validating them on the datasets provided for each package and by testing them on eight different datasets collected over the years in our laboratory. Indoor and outdoor, terrestrial and flying vehicles, in addition to underwater robots, cameras, and buoys were used to collect data. An analysis of the motions required for the different approaches and an evaluation of their performance is presented.

Object discovery and modeling have been widely studied in the computer vision and robotics communities. SLAM approaches that make use of objects and higher level features have also recently been proposed. Using higher level features provides several benefits: these can be more discriminative, which helps data association, and can serve to inform service robotic tasks that require higher level information, such as object models and poses. We propose an approach for online object discovery and object modeling, and extend a SLAM system to utilize these discovered and modeled objects as landmarks to help localize the robot in an online manner. Such landmarks are particularly useful for detecting loop closures in larger maps. In addition to the map, our system outputs a database of detected object models for use in future SLAM or service robotic tasks. Experimental results are presented to demonstrate the approach's ability to detect and model objects, as well as to improve SLAM results by detecting loop closures.

The exploration of unknown environments is a particularly and intuitively detachable problem, allowing the division of robotic teams into smaller groups, or even into individuals, which explore different areas in the environment. While exploring, the team can discretely reassemble and build a joint representation of the region. However, this approach gives rise to a new set of problems, such as communication, synchronization and information fusion. This work presents mrgs, an open source framework for Multi-Robot SLAM. We propose a solution that seeks to provide any system capable of performing single-robot SLAM with the ability to efficiently communicate with its teammates and to build a global representation of the environment based on the information it exchanges with its peers. The solution is validated through experiments conducted over real-world data and we analyze its performance in terms of scalability and communication efficiency.

IngenIería e InvestIgacIón vol. 37 n.° 3, december-2017 (37-44) 37 Detection and location of surfaces in a 3D environment through a single transducer and ultrasonic spherical caps Detección y localización de superficies en un ambiente 3D a través de un solo sensor y casquetes esféricos ultrasónicos ABSTRACT In this paper, an ultrasonic arc map method for flat mapping is extended to three-dimensional space replacing the circumference arcs by spherical caps. An enclosed environment is scanned by employing a single ultrasonic device. The range, position, and orientation of the transducer are used to digitize the uncertainty caps and place them in a three-dimensional map. Through the spatial voting method, the generated voxels are elected in order to distinguish those which mark the true position of an obstacle and discard those that are produced by cross talk, noise, fake ranges, and angular resolution. The results show that it is possible to obtain sufficient information to build a three-dimensional map for navigation by employing inexpensive sensors and a low power data processing.

Large-scale SLAM demands for scalable techniques in which the computational burden and the memory consumption is shared among many processing units. While recent literature offers competitive approaches for scalable mapping, these usually involve approximations to preserve sparsity of the resulting subproblems. We present an approach to scalable SLAM that is exactly sparse. The main insight is that rather than eliminating variables (which induces dense cliques), we split the separators connecting subgraphs. Then, we enforce consistency of the separators in different subgraphs using hard constraints. The resulting constrained optimization problem can be solved in a decentralized manner using the multiblock Alternating Direction Method of Multipliers (ADMM).  Our framework is appealing since (i) it preserves the sparsity structure of the original problem, (ii) it has a straightforward implementation, (iii) it allows to easily trade-off between computation time and  accuracy. While our approach is currently slower than competitors, it is more accurate than other memory efficient alternatives. Moreover, we believe that the proposed framework can be of interest on its own as it draws connections with recent literature on decentralized optimization.

KinectFusion is an impressive algorithm that was introduced in 2011 to simultaneously track the movement of a depth camera in the 3D space and densely reconstruct the environment as a Truncated Signed Distance Formula (TSDF) volume, in real-time. In 2012, we introduced the Moving Volume KinectFusion method that allows the volume/camera move freely in the space. In this work, we further develop the Moving Volume KinectFusion method (as rxKinFu) to fit better to robotic and perception applications, especially for locomotion and manipulation tasks. We describe methods to raycast point clouds from the volume using virtual cameras, and use the point clouds for heightmaps generation (e.g., useful for locomotion) or object dense point cloud extraction (e.g., useful for manipulation). Moreover, we present different methods for keeping the camera fixed with respect to the moving volume, fusing also IMU data and the camera heading/velocity estimation. Last, we integrate and show some demonstrations of rxKinFu on the mini-bipedal robot RPBP, our wheeled quadrupedal robot CENTAURO, and the newly developed full-size humanoid robot COMAN+. We release the code as an open-source package, using the Robotic Operating System (ROS) and the Point Cloud Library (PCL).

— Matching 3D point clouds, a critical operation in map building and localization, is difficult with Velodyne-type sensors due to the sparse and non-uniform point clouds that they produce. Standard methods from dense 3D point clouds are generally not effective. In this paper, we describe a feature-based approach using Principal Components Analysis (PCA) of neighborhoods of points, which results in mathematically principled line and plane features. The key contribution in this work is to show how this type of feature extraction can be done efficiently and robustly even on non-uniformly sampled point clouds. The resulting detector runs in real-time and can be easily tuned to have a low false positive rate, simplifying data association. We evaluate the performance of our algorithm on an autonomous car at the MCity Test Facility using a Velodyne HDL-32E, and we compare our results against the state-of-the-art NARF keypoint detector.

Abstract. This paper presents a novel stereo SLAM framework, where a robust loop chain matching scheme for tracking keypoints is combined with an effective frame selection strategy. The proposed approach, referred to as selective SLAM (SSLAM), relies on the observation that the error in the pose estimation propagates from the uncertainty of the three-dimensional points. This is higher for distant points, corresponding to matches with low temporal flow disparity in the images. Comparative results based on the reference KITTI evaluation framework show that SSLAM is effective and can be implemented efficiently, as it does not require any loop closure or bundle adjustment.

Mapping, real-time localization, and path
planning are prerequisites for autonomous robot nav-
igation. These functions also facilitate situation aware-
ness of remote operators. In this paper, we propose
methods for ecient 3D mapping and real-time 6D
pose tracking of autonomous robots using a continu-
ously rotating 2D laser scanner. We have developed
our approach in the context of the DLR SpaceBot Cup
robotics challenge. Multi-resolution surfel representa-
tions allow for compact maps and ecient registration
of local maps. Real-time pose tracking is performed by a
particle lter observing individual laser scan lines. Ter-
rain drivability is assessed within a global environment
map and used for planning feasible paths. Our approach
is evaluated using challenging real environments.

We outline an approach for using concentration inequalities to perform rapid approximate multi-hypothesis testing.
In a scenario where multiple hypotheses are ranked according to a large set of features, our scheme improves the efficiency of selecting the best hypothesis by providing a “bail-out threshold” at which unpromising hypotheses can be excluded from further evaluation. We show how concentration inequalities can be used to derive principled bail-out thresholds, subject to a user-specified error tolerance.
The technique is similar to the sequential probability ratio test, but is applicable in more general conditions. We apply the technique to improve the speed of the fast-appearance-based mapping system for appearance-based place recognition and mapping. The speed increase provided by the new approach is data dependent, but we demonstrate speed improvements of between 25x − 50x on real data, with only a slight degradation in accuracy.

Indoor  mobile  laser  scanning  (MLS)  systems,  based  on  the  principles  of  simultaneous localization and mapping (SLAM), have become an approved method in recent years to obtain  indoor  environment  data.  2D  and  3D  laser  scanning  systems  based  on  SLAM algorithmshave  now  become  portable  systems hand-heldand  on  the  back.  The  SLAM approach  instantly  determines  the  necessary  positioning  and  mapping  parameters  by using the sensors' data and thus produces data representing the environment in 2D or 3D with point clouds. 3D and 2D building plans provide reference base maps for indoor location and positioning. These data are also of high importance for architectural surveys and  restoration  works,  and  indoor  design.  However,  the  SLAM  process  generating duplicated  and  noisy  point  clouds  causes  challenges  in  defining  the  characteristics  of linear  edges  and  planes.  In  this  study,  preliminary  study  results  of  the  methodology applied  for  the  semi-automatic  drawing  of  a  building  plan  from  a  building  section obtained  from  SLAM  data  are  presented.  With  this  proposed  method,  it  is  provided  to facilitate  indoor  drawings  and  extract  2D  planar  and  geometric  information  from  the complexity  of  3D  point  clouds.  Since  the  proposed  study  is  becoming  an  adaptive methodology, it is a method capable of development, and it is thought that performance criteria can be increased.

Historical shipwrecks are important for many reasons, including historical, tourist, and environmental. Currently, limited efforts for constructing accurate models are performed by divers that need to take measurements manually using a grid and measuring tape, or using handheld sensors. A commercial product, Google Street View 1, contains underwater panoramas from the select locations around the planet including a few shipwrecks, such as the SS Antilla in Aruba and the Yongala at the Great Barrier Reef. However, these panoramas contain no geometric information and thus there are no 3D representations available of these wrecks. This paper provides, first, an evaluation of visual features quality in datasets that span from indoor to underwater ones. Second, by testing some open-source vision-based state estimation packages on different shipwreck datasets, insights on open challenges for shipwrecks mapping are shown. Some good practices for replicable results are also discussed.

In this paper, we present an information-based
approach to select a reduced number of landmarks and poses
for a robot to localize itself and simultaneously build an
accurate map. We develop an information theoretic algorithm
to efficiently reduce the number of landmarks and poses in
a SLAM estimate without compromising the accuracy of the
estimated trajectory. We also propose an incremental version of
the reduction algorithm which can be used in SLAM framework
resulting in information based reduced landmark SLAM. The
results of reduced landmark based SLAM algorithm are shown
on Victoria park dataset and a Synthetic dataset and are
compared with standard graph SLAM (SAM [6]) algorithm.
We demonstrate a reduction of 40-50% in the number of
landmarks and around 55% in the number of poses with
minimal estimation error as compared to standard SLAM
algorithm.

Planning under uncertainty in perception and action requires the robot to be able to use active strategies for trading-off between the contrasting tasks of exploring the scenario and satisfying given constraints on the admissible uncertainty in the estimation process. In this work we compare several state-of-the-art approaches to active SLAM (Simultaneous Localization and Mapping) and exploration using Rao-Blackwellized Particle Filters. The proposed numerical evaluation and analytical insight allow to have a clear picture of the advantages and limitations of each technique for real world applications. Extensive tests are performed in typical indoor and office environments and on well-known benchmarking scenarios belonging to SLAM literature, with the purpose of evaluating the maturity of the field and the potential of truly autonomous navigation systems based on particle filtering.

This paper presents an approach to Simultaneous Localization and Mapping (SLAM) based on monocular vision. Standard multiple-view vision techniques are used to estimate robot motion and scene structure, which are then integrated with minimal odometric information and used to build a global environment map. Preliminary experimental results are also presented and discussed. Key-Words:Robot localisation, Mapping, Monocular vision, SLAM

We present a novel approach which enables a mobile robot to estimate its trajectory in an unknown environment with long-range passive radio-frequency identification (RFID). The estimation is based only on odometry and RFID measurements. The technique requires no prior observation model and makes no assumptions on the RFID setup. In particular, it is adaptive to the power level, the way the RFID antennas are mounted on the robot, and environmental characteristics, which have major impact on long-range RFID measurements. Tag positions need not be known in advance, and only the arbitrary, given infrastructure of RFID tags in the environment is utilized. By a series of experiments with a mobile robot, we show that trajectory estimation is achieved accurately and robustly.

This In robotics, visual-inertial sensor fusion has become one of the most active research topics; optimization-based fusion approaches have gone beyond filtering approaches in terms of robustness and accuracy. For the optimization-based visual-inertial Simultaneous Localization and Mapping (SLAM), accurate initialization is essential for this nonlinear system which requires an accurate estimation of the initial states (Inertial Measurement Unit (IMU) biases, scale, gravity, and velocity). Therefore, our goal is to propose a more robust initialization method. First, we estimate the gyroscope bias, initial scale, and gravity. Then, we use the gravity magnitude to refine the gravity direction by minimizing the error state on the tangent space of the estimated gravity vector. After that, we estimate the accelerometer bias separately from gravity. Finally, based on the condition number and convergence process, we propose a robust and automatic termination criterion to indicate when the initialization is successfully achieved. Additionally, we use all the initial estimated values to initialize a visual-inertial SLAM system. We test our initialization method with different sequences of the public EuRoC dataset, and real-time hand-held experiment in indoor and outdoor environments. The results demonstrated good performance of both the estimated initial state and the automatic termination criterion. They also illustrated that the estimated gravity converges within a short time interval using the refinement approach.

In this study, the movement of mobile robots on a certain path by preserving their formation and with a leader-follower was examined. Knowing the initial and final positions and orientations of the leader robot, the cubic polynomial was used and the positions of the leader at all points on the path were found. Then, the positions, where the followers were found with the homogeneous transformations, were calculated in order to provide the equilateral triangle formation. The velocity profile of the leader was calculated with certain calculations by determining the maximum velocity for the leader. Controller has been designed for the leader's right and left motors. In order to find the velocity of the follower robots, it was calculated by using the position information that the robots should be at a certain moment. The resulting graphics showed how the robots would create a path at certain angles. The distance values that should be between the robots and the location information from the UWB (Ultra-wideband) were shown on the Matlab graphics. The calculated linear velocities and desired velocities of the leader and follower robots are shown graphically. In the control diagram created for the left and right motors of the leader robot, it has been shown how the linear and angular velocities are affected by PID.

3D laser scanners composed of a rotating 2D laser range scanner exhibit different point densities within and between
individual scan lines. Such non-uniform point densities influence neighbor searches which in turn may negatively affect
feature estimation and scan registration. To reliably register such scans, we extend a state-of-the-art registration algorithm
to include topological information from approximate surface reconstructions. We show that our approach outperforms
related approaches in both refining a good initial pose estimate and registering badly aligned point clouds if no such estimate
is available. In an example application, we demonstrate local 3D mapping with a micro aerial vehicle by registering
sequences of non-uniform density point clouds acquired in-flight with a continuously rotating lightweight 3D scanner.
1 Introduction
3D scanners provide robots with the ability to extract spatial
information about their surroundings, detect obstacles
and avoid collisions, build 3D maps, and localize. In
the course of a larger project on mapping inaccessible areas
with autonomous micro aerial vehicles (MAVs), we
have developed a light-weight 3D scanner [13] specifically
suited for the application on MAVs. It consists of
a Hokuyo 2D laser scanner, a rotary actuator and a slip
ring to allow continuous rotation. Just as with other rotated
scanners, the acquired point clouds (aggregated over
one full or half rotation) show the particular characteristic
of having non-uniform point densities: usually a high
density within each scan line and a certain angle between
scan lines which depends on the rotation speed of the scanner
(see Figure 1). In our setup, we aggregate individual
scans of the continuously rotating laser scanner and form
3D point clouds over one half rotation (covering an omnidirectional
field of view). To compensate for the MAV’s
motion during aggregation, we use visual odometry [18]
and inertial sensors as rough estimates, and transform the
scans into a common coordinate frame.
Since we use the laser scanner not only for mapping and
localization but also for collision avoidance, we rotate the
scanner fast resulting in a particularly low angular resolution
of roughly 9. This reduces the point density in
the aggregated point clouds but increases the frequency
with which we perceive (omnidirectionally) the surroundings
of the MAV (2 Hz). The resulting non-uniform point
densities affect classic neighborhood searches in 3D and
cause problems in local feature estimation and registration.
To compensate for the non-uniform point densities,
we extend the state-of-the-art registration algorithm
Generalized-ICP [19] to include topological surface information
instead of the 3D neighborhood of points.
r
u+1 u u-1
Figure 1: Classic neighbor searches in non-uniform density
point clouds may only find points in the same scan
line (red), whereas a topological neighborhood (green) can
better reflect the underlying surface
The remainder of this paper is organized as follows: after
giving a brief overview on related work in Section 2,
we present our approach in Section 3. In experiments, we
demonstrate the superior performance of our approach and
discuss the achieved results in Section 4.
2 RelatedWork
2.1 Laser Scanners for MAVs
For mobile ground robots, 3D laser scanning sensors are
widely used due to their accurate distance measurements
even in bad lighting conditions and their large field-ofview.
For instance, autonomous cars often perceive obstacles
by means of a rotating laser scanner with a 360
horizontal field-of-view, allowing for the detection of obstacles
in every direction [12].
Up to

The development of intelligent surveillance systems is an active research area of increasing interest. In recent years, autonomous or semi-autonomous mobile robots have been adopted as useful means to reduce fixed installations and number of devices needed for surveillance of a given area. In this context SELEX Sistemi Integrati is investigating the possibility to use robots-sensors systems to improve the monitoring of large and populated indoor areas. In particular, the joint use of the Swarm Logic and heterogeneous sensors, some installed at strategic points of the infrastructure and other installed on mobile robots, allows the creation of a very dynamic network of cooperating sensors, that is able to ensure a high level of protection and a fast reaction to threats. In this paper an integrated intelligent system based on swarm logic to improve monitoring performance of large critical infrastructures such as airport terminals, warehouses, railway stations, production facilities is presented. The adopted system architecture, consisting of two hierarchical levels, is introduced and discussed. In each of these levels novel aspects, developed by the team, are present.

Monocular depth has been found using estimation, closed-form solution and learning techniques. Estimation and closed-form solution compute the depth from motion, while learning techniques calculate the depth using a single image with a depth map as a supervisor. This paper presents a new closed form solution for monocular depth from motion. The proposed method builds on the notation that an interest point in an image of a static scene has a static world location. Camera pose and calibration parameters are used as constraints to provide the depth solution. The proposed method is verified through real experiments on indoor mobile robot platform. The effect of uncertainty in the solution variables is studied and the results are benchmarked to groundtruth.

This paper is a survey work for designing a Vision based Simultaneous Localization and Mapping (VSLAM) humanoid robot to generate a map of an unknown environment. A lot of factors have to be considered while designing a VSLAM robot. Vision Sensors are very attractive for application in SLAM because of their rich sensory output and cost effectiveness. Different issues are involved in the problem of vision based SLAM and many different approaches exist in order to solve these issues. Similarly the type of environment determines the suitable feature extraction method. The main objective of this survey is to conduct a comparative study among the current vision sensing methods in terms of imaging systems used for performing VSLAM, feature extraction algorithms used in some recently published papers, and initialization of landmarks, and to figure out the best for our work.