| 1. |
- Fallon, Maurice F., et al.
(författare)
-
Relocating Underwater Features Autonomously Using Sonar-Based SLAM
- 2013
-
Ingår i: IEEE Journal of Oceanic Engineering. - : IEEE Oceanic Engineering Society. - 0364-9059 .- 1558-1691. ; 38:3, s. 500-513
-
Tidskriftsartikel (refereegranskat)abstract
- This paper describes a system for reacquiring features of interest in a shallow-water ocean environment, using autonomous underwater vehicles (AUVs) equipped with low-cost sonar and navigation sensors. In performing mine countermeasures, it is critical to enable AUVs to navigate accurately to previously mapped objects of interest in the water column or on the seabed, for further assessment or remediation. An important aspect of the overall system design is to keep the size and cost of the reacquisition vehicle as low as possible, as it may potentially be destroyed in the reacquisition mission. This low-cost requirement prevents the use of sophisticated AUV navigation sensors, such as a Doppler velocity log (DVL) or an inertial navigation system (INS). Our system instead uses the Proviewer 900-kHz imaging sonar from Blueview Technologies, which produces forward-looking sonar (FLS) images at ranges up to 40 m at approximately 4 Hz. In large volumes, it is hoped that this sensor can be manufactured at low cost. Our approach uses a novel simultaneous localization and mapping (SLAM) algorithm that detects and tracks features in the FLS images to renavigate to a previously mapped target. This feature-based navigation (FBN) system incorporates a number of recent advances in pose graph optimization algorithms for SLAM. The system has undergone extensive field testing over a period of more than four years, demonstrating the potential for the use of this new approach for feature reacquisition. In this report, we review the methodologies and components of the FBN system, describe the system's technological features, review the performance of the system in a series of extensive in-water field tests, and highlight issues for future research.
|
|
| 2. |
- Fallon, Maurice F., et al.
(författare)
-
Simultaneous Localization and Mapping in Marine Environments
- 2013
-
Ingår i: Marine Robot Autonomy. - New York : Springer. - 9781461456582 ; , s. 329-372
-
Bokkapitel (refereegranskat)abstract
- Accurate navigation is a fundamental requirement for robotic systems—marine and terrestrial. For an intelligent autonomous system to interact effectively and safely with its environment, it needs to accurately perceive its surroundings. While traditional dead-reckoning filtering can achieve extremely low drift rates, the localization accuracy decays monotonically with distance traveled. Other approaches (such as external beacons) can help; nonetheless, the typical prerogative is to remain at a safe distance and to avoid engaging with the environment. In this chapter we discuss alternative approaches which utilize onboard sensors so that the robot can estimate the location of sensed objects and use these observations to improve its own navigation as well as its perception of the environment. This approach allows for meaningful interaction and autonomy. Three motivating autonomous underwater vehicle (AUV) applications are outlined herein. The first fuses external range sensing with relative sonar measurements. The second application localizes relative to a prior map so as to revisit a specific feature, while the third builds an accurate model of an underwater structure which is consistent and complete. In particular we demonstrate that each approach can be abstracted to a core problem of incremental estimation within a sparse graph of the AUV’s trajectory and the locations of features of interest which can be updated and optimized in real time on board the AUV.
|
|
| 3. |
- Folkesson, John, 1960-, et al.
(författare)
-
A Feature Based Navigation System for an Autonomous Underwater Robot
- 2008
-
Ingår i: Field And Service Robotics. - Berlin, Heidelberg : Springer Berlin/Heidelberg. - 9783540754039 ; , s. 105-114
-
Konferensbidrag (refereegranskat)abstract
- We present a system for autonomous underwater navigation as implemented on a Nekton Ranger autonomous underwater vehicle, AUV. This is one of the first implementations of a practical application for simultaneous localization and mapping on an AUV. Besides being an application of real-time SLAM, the implemtation demonstrates a novel data fusion solution where data from 7 sources are fused at different time scales in 5 separate estimators. By modularizing the data fusion problem in this way each estimator can be tuned separately to provide output useful to the end goal of localizing the AUV, on an a priori map. The Ranger AUV is equipped with a BlueView blazed array sonar which is used to detect features in the underwater environment. Underwater testing results are presented. The features in these tests are deployed radar reflectors.
|
|
| 4. |
- Folkesson, John, 1960-, et al.
(författare)
-
Autonomy through SLAM for an Underwater Robot
- 2011
-
Ingår i: Robotics Research The 14th International Symposium ISRR. - Berlin, Heidelberg : Springer Berlin/Heidelberg. ; , s. 55-70
-
Konferensbidrag (refereegranskat)abstract
- An autonomous underwater vehicle (AUV) is achieved that integrates state of the art simultaneous localization and mapping (SLAM) into the decision processes. This autonomy is used to carry out undersea target reacquisition missions that would otherwise be impossible with a low-cost platform. The AUV requires only simple sensors and operates without navigation equipment such as Doppler Velocity Log, inertial navigation or acoustic beacons. Demonstrations of the capability show that the vehicle can carry out the task in an ocean environment. The system includes a forward looking sonar and a set of simple vehicle sensors. The functionality includes feature tracking using a graphical square root smoothing SLAM algorithm, global localization using multiple EKF estimators, and knowledge adaptive mission execution. The global localization incorporates a unique robust matching criteria which utilizes both positive and negative information. Separate match hypotheses are maintained by each EKF estimator allowing all matching decisions to be reversible.
|
|
| 5. |
- Folkesson, John, 1960-, et al.
(författare)
-
Feature tracking for underwater navigation using sonar
- 2007
-
Ingår i: Proceedings of the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems San Diego, CA, USA, Oct 29 - Nov 2, 2007. - : IEEE conference proceedings. - 9781424409129 ; , s. 3678-3684
-
Konferensbidrag (refereegranskat)abstract
- Tracking sonar features in real time on an underwater robot is a challenging task. One reason is the low observability of the sonar in some directions. For example, using a blazed array sonar one observes range and the angle to the array axis with fair precision. The angle around the axis is poorly constrained. This situation is problematic for tracking features in world frame Cartesian coordinates as the error surfaces will not be ellipsoids. Thus Gaussian tracking of the features will not work properly. The situation is similar to the problem of tracking features in camera images. There the unconstrained direction is depth and its errors are highly non-Gaussian. We propose a solution to the sonar problem that is analogous to the successful inverse depth feature parameterization for vision tracking, introduced by [1]. We parameterize the features by the robot pose where it was first seen and the range/bearing from that pose. Thus the 3D features have 9 parameters that specify their world coordinates. We use a nonlinear transformation on the poorly observed bearing angle to give a more accurate Gaussian approximation to the uncertainty. These features are tracked in a SLAM framework until there is enough information to initialize world frame Cartesian coordinates for them. The more compact representation can then be used for a global SLAM or localization purposes. We present results for a system running real time underwater SLAM/localization. These results show that the parameterization leads to greater consistency in the feature location estimates.
|
|
| 6. |
- Torroba, Ignacio, 1992-
(författare)
-
Data-driven Approaches to Uncertainty Modelling for SLAM in the Open Sea
- 2022
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Autonomous underwater vehicles (AUVs) equipped with multibeam echo-sounders have become indispensable tools for bathymetric mapping due to their ability to reach seabed regions inaccessible to surface vessels. However, the closer proximity to the survey area comes at the expense of a growing error in the AUV global pose estimate due to the lack of prior maps or a geo-referencing system underwater, such as GPS. This limitation, together with the changing environment dynamics in deep sea waters and the scale of the areas to map, makes simultaneous localization and mapping (SLAM) a necessary enabler for long-range, reliable and safe AUV navigation in open sea missions.SLAM has allowed the safe deployment of self-driving cars on the streets and service robots in our homes, but remains a challenge in the deep sea domain. This is due to the constrained sensing capabilities available underwater and the scarcity of distinguishable features in the seabed. As a result of these, successful place recognition is infrequent, yielding loop closure (LC) detections more sparse and therefore more crucial. To adequately factor in each LC constraint in a SLAM back-end, their uncertainties need to be carefully parameterized to weight their influence in the final AUV trajectory estimate. Thus, this thesis is concerned with modelling these uncertainties, in particular when analytical models cannot be derived, focusing instead in data-driven methods. We present our contributions in three key SLAM areas targeting this problem. First, our work on inferring the uncertainties in the bathymetric submap registration process shows how deep learning techniques can be successfully applied to learning noise models directly from raw data and without ground truth position information. We further show how the predicted uncertainties improve the convergence of submap-based graph-SLAM solutions in AUV surveys.Secondly, we introduce a methodology to construct terrain representations with Stochastic Variational Gaussian processes (SVGP) propagating the AUV localization and sensors uncertainties into the final maps. The proposed approach is not limited to any GP kernel or noise model in the data and can handle datasets of millions of training points. The experiments demonstrate how the learned terrain models yield improved particle filter estimates in AUV localization problems.Finally, we adapt the previous SVGP mapping approach to online bathymetric learning and demonstrate its scalability and flexibility in a Rao-Blackwellized SLAM framework. The presented RBPF-SVGP solution is capable of maintaining up to 100 particles in parallel, each with a single SVGP map capable of regressing entire surveys. Our results show how the RBPF-SVGP can perform in real time in an embedded platform and can be executed live in an AUV.Additionally, all the implementations proposed have been made publicly available to promote further research in underwater SLAM and the adoption of common open-source frameworks, datasets and benchmarks in the field.
|
|
| 7. |
- Alberti, Marina, et al.
(författare)
-
Relational approaches for joint object classification andscene similarity measurement in indoor environments
- 2014
-
Ingår i: Proc. of 2014 AAAI Spring Symposium QualitativeRepresentations for Robots 2014. - Palo Alto, California : The AAAI Press.
-
Konferensbidrag (refereegranskat)abstract
- The qualitative structure of objects and their spatial distribution,to a large extent, define an indoor human environmentscene. This paper presents an approach forindoor scene similarity measurement based on the spatialcharacteristics and arrangement of the objects inthe scene. For this purpose, two main sets of spatialfeatures are computed, from single objects and objectpairs. A Gaussian Mixture Model is applied both onthe single object features and the object pair features, tolearn object class models and relationships of the objectpairs, respectively. Given an unknown scene, the objectclasses are predicted using the probabilistic frameworkon the learned object class models. From the predictedobject classes, object pair features are extracted. A fi-nal scene similarity score is obtained using the learnedprobabilistic models of object pair relationships. Ourmethod is tested on a real world 3D database of deskscenes, using a leave-one-out cross-validation framework.To evaluate the effect of varying conditions on thescene similarity score, we apply our method on mockscenes, generated by removing objects of different categoriesin the test scenes.
|
|
| 8. |
- Ambrus, Rares, et al.
(författare)
-
Autonomous meshing, texturing and recognition of object models with a mobile robot
- 2017
-
Ingår i: 2017 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS). - Vancouver, Canada : IEEE. - 9781538626825 ; , s. 5071-5078
-
Konferensbidrag (refereegranskat)abstract
- We present a system for creating object models from RGB-D views acquired autonomously by a mobile robot. We create high-quality textured meshes of the objects by approximating the underlying geometry with a Poisson surface. Our system employs two optimization steps, first registering the views spatially based on image features, and second aligning the RGB images to maximize photometric consistency with respect to the reconstructed mesh. We show that the resulting models can be used robustly for recognition by training a Convolutional Neural Network (CNN) on images rendered from the reconstructed meshes. We perform experiments on data collected autonomously by a mobile robot both in controlled and uncontrolled scenarios. We compare quantitatively and qualitatively to previous work to validate our approach.
|
|
| 9. |
- Ambrus, Rares, et al.
(författare)
-
Meta-rooms : Building and Maintaining Long Term Spatial Models in a Dynamic World
- 2014
-
Ingår i: 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, (IROS 2014). - : IEEE conference proceedings. - 9781479969340 ; , s. 1854-1861
-
Konferensbidrag (refereegranskat)abstract
- We present a novel method for re-creating the static structure of cluttered office environments -which we define as the " meta-room" -from multiple observations collected by an autonomous robot equipped with an RGB-D depth camera over extended periods of time. Our method works directly with point clusters by identifying what has changed from one observation to the next, removing the dynamic elements and at the same time adding previously occluded objects to reconstruct the underlying static structure as accurately as possible. The process of constructing the meta-rooms is iterative and it is designed to incorporate new data as it becomes available, as well as to be robust to environment changes. The latest estimate of the meta-room is used to differentiate and extract clusters of dynamic objects from observations. In addition, we present a method for re-identifying the extracted dynamic objects across observations thus mapping their spatial behaviour over extended periods of time.
|
|
| 10. |
- Ambrus, Rares
(författare)
-
Unsupervised construction of 4D semantic maps in a long-term autonomy scenario
- 2017
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Robots are operating for longer times and collecting much more data than just a few years ago. In this setting we are interested in exploring ways of modeling the environment, segmenting out areas of interest and keeping track of the segmentations over time, with the purpose of building 4D models (i.e. space and time) of the relevant parts of the environment.Our approach relies on repeatedly observing the environment and creating local maps at specific locations. The first question we address is how to choose where to build these local maps. Traditionally, an operator defines a set of waypoints on a pre-built map of the environment which the robot visits autonomously. Instead, we propose a method to automatically extract semantically meaningful regions from a point cloud representation of the environment. The resulting segmentation is purely geometric, and in the context of mobile robots operating in human environments, the semantic label associated with each segment (i.e. kitchen, office) can be of interest for a variety of applications. We therefore also look at how to obtain per-pixel semantic labels given the geometric segmentation, by fusing probabilistic distributions over scene and object types in a Conditional Random Field.For most robotic systems, the elements of interest in the environment are the ones which exhibit some dynamic properties (such as people, chairs, cups, etc.), and the ability to detect and segment such elements provides a very useful initial segmentation of the scene. We propose a method to iteratively build a static map from observations of the same scene acquired at different points in time. Dynamic elements are obtained by computing the difference between the static map and new observations. We address the problem of clustering together dynamic elements which correspond to the same physical object, observed at different points in time and in significantly different circumstances. To address some of the inherent limitations in the sensors used, we autonomously plan, navigate around and obtain additional views of the segmented dynamic elements. We look at methods of fusing the additional data and we show that both a combined point cloud model and a fused mesh representation can be used to more robustly recognize the dynamic object in future observations. In the case of the mesh representation, we also show how a Convolutional Neural Network can be trained for recognition by using mesh renderings.Finally, we present a number of methods to analyse the data acquired by the mobile robot autonomously and over extended time periods. First, we look at how the dynamic segmentations can be used to derive a probabilistic prior which can be used in the mapping process to further improve and reinforce the segmentation accuracy. We also investigate how to leverage spatial-temporal constraints in order to cluster dynamic elements observed at different points in time and under different circumstances. We show that by making a few simple assumptions we can increase the clustering accuracy even when the object appearance varies significantly between observations. The result of the clustering is a spatial-temporal footprint of the dynamic object, defining an area where the object is likely to be observed spatially as well as a set of time stamps corresponding to when the object was previously observed. Using this data, predictive models can be created and used to infer future times when the object is more likely to be observed. In an object search scenario, this model can be used to decrease the search time when looking for specific objects.
|
|
