No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
Robotique coopérative aéro-terrestre : Localisation et cartographie hétérogène
Abstract
Les travaux de cette thèse adressent la problématique de la coopération aéro-terrestre pour la cartographie de l’espace navigable. La nécessité d’une carte pour la navigation et la planification de chemins pour les robots terrestres n’est plus à prouver. L’utilisation d’une coopération aéro-terrestre pour créer une carte navigable à destination du robot terrestre a plusieurs intérêts. Premièrement, le drone peut cartographier rapidement une zone grâce à son champ de vision étendu et ses capacités de déplacement. Deuxièmement, la fusion des cartes créées par ces deux agents permet de tirer le meilleur profit des deux points de vue : la cohérence de la vue aérienne globale et la précision de la vue terrestre locale. Pour répondre à cette problématique, nous proposons une méthode qui s’appuie sur la création de cartes hybrides et leur fusion. Les cartes sont construites en utilisant le squelette de l’espace navigable terrestre comme support d’un graphe contenant également des informations métriques locales de l’environnement. La mise en correspondance des cartes aérienne et terrestre s’effectue à l’aide d’un appariement point à point déterminé grâce à une mesure de dissimilarité appropriée. Cette dernière est définie pour répondre aux critères d’invariance et de discriminance dans ce contexte. La mise en correspondance est ensuite utilisée pour fusionner les cartes entre elles. Les cartes fusionnées peuvent être utilisées par le robot au sol pour effectuer sa mission. Elles permettent également de propager des informations telles que des coordonnées GPS à des robots et dans des lieux où ce dispositif n’est pas disponible. Des expérimentations en environnements virtuels et réels sont réalisées pour valider cette approche et en tracer les perspectives.
ResearchGate has not been able to resolve any citations for this publication.
Traditional approaches for simultaneous localization and mapping (SLAM) rely on geometric features such as points, lines, and planes to infer the environment structure. They make hard decisions about the (data) association between observed features and mapped landmarks to update the environment model. This paper makes two contributions to the state of the art in SLAM. First, it generalizes the purely geometric model by introducing semantically meaningful objects, represented as structured models of mid-level part features. Second, instead of making hard, potentially wrong associations between semantic features and objects, it shows that SLAM inference can be performed efficiently with probabilistic data association. The approach not only allows building meaningful maps (containing doors, chairs, cars, etc.) but also offers significant advantages in ambiguous environments.
In this paper, by a novel morphological decomposition method, we propose an efficient compression approach. Our presented decomposition arises from solving a minimum set cover problem (MSCP) obtained from the image skeleton data. We first use the skeleton pixels to create a collection of blocks which cover the foreground. The given blocks are both overlapped and too many. Hence, in order to find the minimum number of the blocks that cover the foreground, we form an MCSP. To solve this problem, we present a new algorithm of which accuracy is better than those of the known methods in the literatures. Also, its error analysis is studied to obtain an error bound. In the sequel, we present a fast algorithm which include an extra parameter by which the relation between the accuracy and CPU time can be controlled. Finally, several examples are given to confirm the efficiency of our approach.
This work presents our results on 3D robot localization, mapping and path planning for the latest joint exercise of the European project “Long-Term Human-Robot Teaming for Robots Assisted Disaster Response” (TRADR) 1 . The full system is operated and evaluated by firemen end-users in real-world search and rescue experiments. We demonstrate that the system is able to plan a path to a goal position desired by the fireman operator in the TRADR Operational Control Unit (OCU), using a persistent 3D map created by the robot during previous sorties.
Simultaneous Localization and Mapping (SLAM) consists in the concurrent construction of a representation of the environment (the map), and the estimation of the state of the robot moving within it. The SLAM community has made astonishing progress over the last 30 years, enabling large-scale real-world applications, and witnessing a steady transition of this technology to industry. We survey the current state of SLAM. We start by presenting what is now the de-facto standard formulation for SLAM. We then review related work, covering a broad set of topics including robustness and scalability in long-term mapping, metric and semantic representations for mapping, theoretical performance guarantees, active SLAM and exploration, and other new frontiers. The paper serves as a tutorial for the non-expert reader. It is also a position paper: by looking at the published research with a critical eye, we delineate open challenges and new research issues, that still deserve careful scientific investigation. The paper also contains the authors' take on two questions that often animate discussions during robotics conferences: do robots need SLAM? Is SLAM solved?
Visual place recognition is a challenging problem due to the vast range of ways in which the appearance of real-world places can vary. In recent years, improvements in visual sensing capabilities, an ever-increasing focus on long-term mobile robot autonomy, and the ability to draw on state-of-the-art research in other disciplines—particularly recognition in computer vision and animal navigation in neuroscience—have all contributed to significant advances in visual place recognition systems. This paper presents a survey of the visual place recognition research landscape. We start by introducing the concepts behind place recognition—the role of place recognition in the animal kingdom, how a “place” is defined in a robotics context, and the major components of a place recognition system. Long-term robot operations have revealed that changing appearance can be a significant factor in visual place recognition failure; therefore, we discuss how place recognition solutions can implicitly or explicitly account for appearance change within the environment. Finally, we close with a discussion on the future of visual place recognition, in particular with respect to the rapid advances being made in the related fields of deep learning, semantic scene understanding, and video description.
This paper addresses initial efforts to develop a navigation system for ground vehicles supported by visual
feedback from a mini aerial vehicle. A visual-based algorithm computes the ground vehicle pose in the world frame, as well as possible obstacles within the ground vehicle pathway. Relying on that information, a navigation and obstacle avoidance system is used to re-plan the ground vehicle trajectory, ensuring an optimal detour. Finally, some experiments are presented employing a unmanned ground vehicle (UGV) and a low cost mini unmanned aerial vehicle (UAV).
Graph-based Simultaneous Localization and Mapping (SLAM) has experienced a recent surge towards robust methods. These methods take the combinatorial aspect of data association into account by allowing decisions of the graph topology to be made during optimization. In this paper, the Generalized Graph SLAM framework for SLAM under ambiguous data association is presented, and a formal description of using hyperedges to encode uncertain loop closures is given for the first time. The framework combines both hyperedges and multimodal Mixture of Gaussian constraints to cover all sources of ambiguity in SLAM. An extension of the authors' multimodal Prefilter method is developed to find good initial conditions in such a generalized multimodal hypergraph. Experiments on a real world 3D dataset show that the novel multimodal hypergraph Prefilter method is both significantly more robust and faster than other robust state-of-the-art methods.
This paper presents a novel decentralized interactive architecture for aerial
and ground mobile robots cooperation. The aerial mobile robot is used to
provide a global coverage during an area inspection, while the ground mobile
robot is used to provide a local coverage of ground features. We include a
human-in-the-loop to provide waypoints for the ground mobile robot to progress
safely in the inspected area. The aerial mobile robot follows continuously the
ground mobile robot in order to always keep it in its coverage view.
This paper presents ORB-SLAM, a feature-based monocular SLAM system that operates in real time, in small and large, indoor and outdoor environments. The system is robust to severe motion clutter, allows wide baseline loop closing and relocalization, and includes full automatic initialization. Building on excellent algorithms of recent years, we designed from scratch a novel system that uses the same features for all SLAM tasks: tracking, mapping, relocalization, and loop closing. A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation. We present an exhaustive evaluation in 27 sequences from the most popular datasets. ORB-SLAM achieves unprecedented performance with respect to other state-of-the-art monocular SLAM approaches. For the benefit of the community, we make the source code public.
We present in this paper a decentralized multi-robot (aerial and ground) cooperation scheme for objects trans-portation. A team of ground mobile robots guided by a drone and a human operator moves in a coordinated way keeping a predefined formation in order to carry objects (tools, gas masks,...) in unsafe industrial areas. One ground mobile robot (leader) navigates among obstacles thanks to the waypoints provided by the drone and the human operator. The other ground mobile robots (followers) use a predictive vision based target tracking controller to keep a certain distance and bearing to the leader.
We propose a new method for the localization of a Micro Aerial Vehicle (MAV) with respect to a ground robot. We solve the problem of registering the 3D maps computed by the robots using different sensors: a dense 3D reconstruction from the MAV monocular camera is aligned with the map computed from the depth sensor on the ground robot. Once aligned, the dense reconstruction from the MAV is used to augment the map computed by the ground robot, by extending it with the information conveyed by the aerial views. The overall approach is novel, as it builds on recent developments in live dense reconstruction from moving cameras to address the problem of air-ground localization. The core of our contribution is constituted by a novel algorithm integrating dense reconstructions from monocular views, Monte Carlo localization, and an iterative pose refinement. In spite of the radically different vantage points from which the maps are acquired, the proposed method achieves high accuracy whereas appearance-based, state-of-the-art approaches fail. Experimental validation in indoor and outdoor scenarios reported an accuracy in position estimation of 0.08 meters and real time performance. This demonstrates that our new approach effectively overcomes the limitations imposed by the difference in sensors and vantage points that negatively affect previous techniques relying on matching visual features.
A fault-tolerant method for stabilization and navigation of 3D heterogeneous formations is proposed in this paper. The presented Model Predictive Control (MPC) based approach enables to deploy compact formations of closely cooperating autonomous aerial and ground robots in surveillance scenarios without the necessity of a precise external localization. Instead, the proposed method relies on a top-view visual relative localization provided by the micro aerial vehicles flying above the ground robots and on a simple yet stable visual based navigation using images from an onboard monocular camera. The MPC based schema together with a fault detection and recovery mechanism provide a robust solution applicable in complex environments with static and dynamic obstacles. The core of the proposed leader-follower based formation driving method consists in a representation of the entire 3D formation as a convex hull projected along a desired path that has to be followed by the group. Such an approach provides non-collision solution and respects requirements of the direct visibility between the team members. The uninterrupted visibility is crucial for the employed top-view localization and therefore for the stabilization of the group. The proposed formation driving method and the fault recovery mechanisms are verified by simulations and hardware experiments presented in the paper.
Topological navigation consists for a robot in navigating in a topological graph which nodes are topological places. Either for indoor or outdoor environments, segmentation into topological places is a challenging issue. In this paper, we propose a common approach for indoor and outdoor environment segmentation without elaborating a complete topological navigation system. The approach is novel in that environment sensing is performed using spherical images. Environment structure estimation is performed by a global structure descriptor specially adapted to the spherical representation. This descriptor is processed by a custom designed algorithm which detects change-points defining the segmentation between topological places.
There are many outdoor robotic applications where a robot must reach a goal position or explore an area without previous knowledge of the environment around it. Additionally, other applications (like path planning) require the use of known maps or previous information of the environment. This work presents a system composed by a terrestrial and an aerial robot that cooperate and share sensor information in order to address those requirements. The ground robot is able to navigate in an unknown large environment aided by visual feedback from a camera on board the aerial robot. At the same time, the obstacles are mapped in real-time by putting together the information from the camera and the positioning system of the ground robot. A set of experiments were carried out with the purpose of verifying the system applicability. The experiments were performed in a simulation environment and outdoor with a medium-sized ground robot and a mini quad-rotor. The proposed robotic system shows outstanding results in simultaneous navigation and mapping applications in large outdoor environments.
We address the problem of deploying groups of tens or hundreds of unmanned ground vehicles (UGVs) in urban environments where
a group of aerial vehicles (UAVs) can be used to coordinate the ground vehicles. We envision a hierarchy in which UAVs with
aerial cameras can be used to monitor and command a swarm of UGVs, controlling the splitting and merging of the swarm into
groups and the shape (distribution) and motion of each group. We call these UAVs Aerial Shepherds. We show a probabilistic approach using the EM algorithm for the initial assignment of shepherds to groups and present behaviors
that allow an efficient hierarchical decomposition. We illustrate the framework through simulation examples, with applications
to deployment in an urban environment.
In this paper, we present incremental smoothing and mapping (iSAM), which is a novel approach to the simultaneous localization and mapping problem that is based on fast incremental matrix factorization. iSAM provides an efficient and exact solution by updating a QR factorization of the naturally sparse smoothing information matrix, thereby recalculating only those matrix entries that actually change. iSAM is efficient even for robot trajectories with many loops as it avoids unnecessary fill-in in the factor matrix by periodic variable reordering. Also, to enable data association in real time, we provide efficient algorithms to access the estimation uncertainties of interest based on the factored information matrix. We systematically evaluate the different components of iSAM as well as the overall algorithm using various simulated and real-world datasets for both landmark and pose-only settings.
Local image features are used for a wide range of applications in computer vision and range imaging. While there is a great variety of detector-descriptor combinations for image data and 3D point clouds, there is no general method readily available for 2D range data. For this reason, the paper first proposes a set of benchmark experiments on detector repeatability and descriptor matching performance using known indoor and outdoor data sets for robot navigation. Secondly, the paper introduces FLIRT that stands for Fast Laser Interest Region Transform, a multi-scale interest region operator for 2D range data. FLIRT combines the best detector with the best descriptor, experimentally found in a comprehensive analysis of alternative detector and descriptor approaches. The analysis yields repeatability and matching performance results similar to the values found for features in the computer vision literature, encouraging a wide range of applications of FLIRT on 2D range data. We finally show how FLIRT can be used in conjunction with RANSAC to address the loop closing/global localization problem in SLAM in indoor as well as outdoor environments. The results demonstrate that FLIRT features have a great potential for robot navigation in terms of precision-recall performance, efficiency and generality.
The generalized Voronoi graph (GVG) is a topological representation of an environment that can be incrementally constructed with a mobile robot using sensor-based control. However, because of sensor range limitations, the GVG control law will fail when the robot moves into a large open area. This paper discusses an extended GVG approach to topological navigation and mapping: the saturated generalized Voronoi graph (S-GVG), for which the robot employs an additional wall-following behavior to navigate along obstacles at the range limit of the sensor. In this paper, we build upon previous work related to the S-GVG and provide two important contributions: 1) a rigorous discussion of the control laws and algorithm modifications that are necessary for incremental construction of the S-GVG with a mobile robot, and 2) a method for incorporating the S-GVG into a novel multi-hypothesis SLAM algorithm for loop-closing and localization. Experiments with a wheeled mobile robot in an office-like environment validate the effectiveness of the proposed approach.
This paper addresses the cooperative localization and visual mapping problem for multiple aerial and ground robots.We propose
the use of heterogeneous visual landmarks, points and line segments. A large-scale SLAM algorithm is generalized to manage
multiple robots, in which a global graph maintains the topological relationships between a series of local sub-maps built
by the different robots. Only single camera setups are considered: in order to achieve undelayed initialization, we present
a novel parametrization for lines based on anchored Plücker coordinates, to which we add extensible endpoints to enhance their
representativeness. The built maps combine such lines with 3D points parametrized in inverse-depth. The overall approach is
evaluated with real-data taken with a helicopter and a ground rover in an abandoned village.
This paper illustrates the methods and results of two sets of experiments in which a group of mobile robots, called s-bots, are required to physically connect to each other—i.e., to self- assemble—to cope with environmental conditions that prevent them to carry out their task in- dividually. The first set of experiments is a pioneering study on the utility of self-assembling robots to address relatively complex scenarios, such as cooperative object trasport. The results of our work suggest that the s-bots possess hardware characteristics which facilitate the design of control mechanisms for autonomous self-assembly. The second set of experiments is an attempt to integrate within the behavioural repertoire of an s-bot decision making mechanisms to allow the robot to autonomously decide whether or not environmental contingencies require self-assembly. The results show that it is possible to synthesise, by using evolutionary computation techniques, artificial neural networks that integrate both the mechanisms for sensory-motor coordination and for decision making required by the robots in the context of self-assembly.
Robotic Construction Crew (RCC) is a heteroge- neous multi-robot system for autonomous acquisition, trans- port, and precision mating of components in construction tasks. RCC minimizes use of resources constrained by a space environment such as computation, power, communi- cation, and sensing. A behavior-based architecture provides adaptability and robustness despite low computational re- quirements. RCC successfully performs several construction related tasks in an emulated outdoor environment despite high levels of uncertainty in motions and sensing. This pa- per provides quantitative results for formation keeping in component transport, precision instrument placement, and construction tasks. Keyword Multi-robot systems . Cooperative transport . Space robotics . Robotic construction
This paper describes a method for spatial representation, place recognition and qualitative self-localization in dynamic indoor environments, based on omnidirectional images. This is a difficult problem because of the perceptual ambiguity of the acquired images, and their weak robustness to noise, geometrical and photometric variations of real world scenes. The spatial representation is built up invariant signatures using Invariance Theory where we suggest to adapt Haar invariant integrals to the particular geometry and image transformations of catadioptric omnidirectional sensors. It follows that combining simple image features in a process of integration over visual transformations and robot motion, can build discriminant percepts about robot spatial locations. We further analyze the invariance properties of the signatures and the apparent relation between their similarity measures and metric distances. The invariance properties of the signatures can be adapted to infer a hierarchical process, from global room recognition to local and coarse robot localization.
The approach is validated in real world experiments and compared to some local and global state-of-the-art methods. The results demonstrate a very interesting performance of the proposed approach and show distinctive behaviors of global and local methods. The invariant signature method, while being very time and memory efficient, provides good separability results similarly to approaches based on local features.
Current technological developments and application-driven demands are bringing us closer to the realization of au- tonomous multirobot systems performing increasingly com- plex missions. However, existing methods of distributing mis- sion subcomponents among multirobot teams do not explicitly handle the required complexity and instead treat tasks as sim- ple indivisible entities, ignoring any inherent structure and se- mantics that such complex tasks might have. These task prop- erties can be exploited to produce more efficient team plans by giving individual robots the ability to come up with new, more localized ways to perform a task; by allowing multiple robots to cooperate by sharing the subcomponents of a task; or both. In this paper, we describe the complex task allocation prob- lem and present a distributed solution for efficiently allocating a set of complex tasks among a robot team. Complex tasks are tasks that can be solved in many possi- ble ways. In contrast, simple tasks can be accomplished in a straightforward, prescriptive manner. The current scope of our work is currently limited to complex tasks that can be de- composed into multiple subtasks related by Boolean logic op- erators. Our solution to multirobot coordination for complex tasks extends market-based approaches by generalizing task descriptions into task trees, which allows tasks to be traded in a market setting at variable levels of abstraction. In order to incorporate these task structures into a market mechanism, novel and efficient bidding and auction clearing algorithms are required. As an example scenario, we focus on an area recon- naissance problem which requires sensor coverage by a team of robots over a set of defined areas of interest. The advan- tages of explicitly modeling complex tasks during the alloca- tion process is demonstrated by a comparison of our approach with existing task allocation algorithms in this application do-
This article overviews the concepts of distributed intelligence, outlining the motivations for studying this field of research. First, common systems of distributed intelligence are classified based upon the types of interactions exhibited, since the type of interaction has relevance to the solution paradigm to be used. We outline three common paradigms for distributed intelligence — the bioinspired paradigm, the organizational and social paradigm, and the knowledge-based, ontological paradigm — and give examples of how these paradigms can be used in multi-robot systems. We then look at a common problem in multi- robot systems — that of task allocation — and show how the solution approach to this problem is very different depending upon the paradigm chosen for abstracting the problem. Our conclusion is that the paradigms are not interchangeable, but rather the selection of the appropriate paradigm is dependent upon the specific constraints and requirements of the application of interest. Further work is needed to provide guidance to the system designer on selecting the proper abstraction, or paradigm, for a given problem.crew, the landing signal officers, ordnancemen, plane handlers, etc. As humans have clearly learned, these teams can very efficiently solve complex tasks by making use of specialists who work together productively. The objective of distributed intelligence in computer science (and related fields) is to generate systems of software agents, robots, sensors, computer systems, and even people and ani- mals (such as search and rescue dogs) that can work together with the same level of efficiency and expertise as human teams. Clearly, such systems could address many important challenges, including not only urban search and rescue, but also military network-centric operations, gaming technologies and simulation, computer security, transportation and logistics, and many others. As a research topic, the study of distributed intelligence
We propose a convex-concave programming approach for the labeled weighted graph matching problem. The convex-concave programming formulation is obtained by rewriting the weighted graph matching problem as a least-square problem on the set of permutation matrices and relaxing it to two different optimization problems: a quadratic convex and a quadratic concave optimization problem on the set of doubly stochastic matrices. The concave relaxation has the same global minimum as the initial graph matching problem, but the search for its global minimum is also a hard combinatorial problem. We, therefore, construct an approximation of the concave problem solution by following a solution path of a convex-concave problem obtained by linear interpolation of the convex and concave formulations, starting from the convex relaxation. This method allows to easily integrate the information on graph label similarities into the optimization problem, and therefore, perform labeled weighted graph matching. The algorithm is compared with some of the best performing graph matching methods on four data sets: simulated graphs, QAPLib, retina vessel images, and handwritten Chinese characters. In all cases, the results are competitive with the state of the art.
This thesis mainly deal with planar areas detection from monocular images and low-budget sensors. These works allow safe landing area detection for UAV and ground/air coopération with traversability maps fusion. In using homographies' properties, we segment the regions of images that are the projections of a plane surface. An extensive study has been made on robust linear estimators in a context of homography estimation from matched points. Synthesis datas were used in order to highlight the influence of the parameters of the environment on the quality of estimated homographies. These results were confronted thereafter with real data. These techniques allow the segmentation of matched points belonging to a plane zone. In order to produce a dense description (continues) of planar zones, we proposed an improvement of the Zero-mean Normal Cross Correlation score. By considering an adaptive model of the influence of the luminosity variances on the scores of correlation, we introduced an automatic segmentation method of planar zones which offer good results. The introduction of probabilistic models enabled us to fuze iteratively the observations, and to build local grids which represent the probability of flatness on zones. Finally with the aim of the co-operation between air and terrestrial robots, we extended this work to the context of terrestrial robotics and the fusion of aéro-terrestrial models.
This paper presents a large-scale 3D environment mapping solution for mobile robots that is based on hybrid metric-topological maps. If a robot performs simultaneous localization and mapping (SLAM) while exploring an unknown environment, sometimes loops are closed and the whole SLAM graph has to be optimized. If a conventional occupancy grid mapping algorithm using a monolithic map is used, the whole occupancy grid map has to be rebuilt after optimization, which for large maps can easily become too time consuming for real-time operation. In the same way, path planning on very large occupancy grid maps can become computationally too expensive. Hybrid metric-topological maps can solve both problems. The global metric map is divided into sub-maps and a global topological graph is formed on the map. This allows recomputing only isolated areas of the map, whereas others can remain unchanged. The topological graph allows efficient path planning on the hybrid map. We show that the hybrid mapping approach presented here is considerably faster than conventional methods. Within the same time, it can generate more detailed maps of large environments. The computation time for maps with identical level of detail can be improved by up to two orders of magnitude.
In robotics, grid maps are often used for solving tasks like collision checking, path planning, and localization. Many approaches to these problems use Euclidean distance maps (DMs), generalized Voronoi diagrams (GVDs), or configuration space (c-space) maps. A key challenge for their application in dynamic environments is the efficient update after potential changes due to moving obstacles or when mapping a previously unknown area. To this end, this paper presents novel algorithms that perform incremental updates that only visit cells affected by changes. Furthermore, we propose incremental update algorithms for DMs and GVDs in the configuration space of non-circular robots. These approaches can be used to implement highly efficient collision checking and holonomic path planning for these platforms. Our c-space representations benefit from parallelization on multi-core CPUs and can also be integrated with other state-of-the-art path planners such as rapidly-exploring random trees. In various experiments using real-world data we show that our update strategies for DMs and GVDs require substantially less cell visits and computation time compared to previous approaches. Furthermore, we demonstrate that our GVD algorithm deals better with non-convex structures, such as indoor areas. All our algorithms consider actual Euclidean distances rather than grid steps and are easy to implement. An open source implementation is available online.
Over the past couple of years, with the development of efficient control algorithms, micro aerial vehicles have come into the picture. In this paper, we consider the problem of creating a map of an indoor environment which provides more information than a 2D map and at the same time is more accurate than the contemporary 3D mapping algorithms. We propose a novel collaborative system, consisting of an unmanned ground vehicle and a micro aerial vehicle, which is used to create augmented 2D maps using the distinct sensing capabilities of these two robots. This system works in a collaborative manner such that the two robots complement each others movement and sensing capabilities.
Most of the existing appearance based topological mapping algorithms produce dense topological maps in which each image stands as a node in the topological graph. Sparser maps can be built by representing groups of visually similar images of a sequence as nodes of a topological graph. In this paper, we present a sparse/hierarchical topological mapping framework which uses Image Sequence Partitioning (ISP) to group visually similar images of a sequence as nodes which are then connected on occurrence of loop closures to form a topological graph. An indexing data structure called Hierarchical Inverted File (HIF) is proposed to store the sparse maps so as to perform loop closure at the two different resolutions of the map namely the node level and image level. TFIDF weighting is combined with spatial and frequency constraints on the detected features for improved loop closure robustness. Our approach is compared with two other existing sparse mapping approaches which use ISP. Sparsity, efficiency and accuracy of the resulting maps are evaluated and compared to that of the other two techniques on publicly available outdoor omni-directional image sequences.
Learning and then recognizing a route, whether travelled during the day or at night, in clear or inclement weather, and in summer or winter is a challenging task for state of the art algorithms in computer vision and robotics. In this paper, we present a new approach to visual navigation under changing conditions dubbed SeqSLAM. Instead of calculating the single location most likely given a current image, our approach calculates the best candidate matching location within every local navigation sequence. Localization is then achieved by recognizing coherent sequences of these “local best matches”. This approach removes the need for global matching performance by the vision front-end - instead it must only pick the best match within any short sequence of images. The approach is applicable over environment changes that render traditional feature-based techniques ineffective. Using two car-mounted camera datasets we demonstrate the effectiveness of the algorithm and compare it to one of the most successful feature-based SLAM algorithms, FAB-MAP. The perceptual change in the datasets is extreme; repeated traverses through environments during the day and then in the middle of the night, at times separated by months or years and in opposite seasons, and in clear weather and extremely heavy rain. While the feature-based method fails, the sequence-based algorithm is able to match trajectory segments at 100% precision with recall rates of up to 60%.
We introduce spatially targeted communication - a communication method for multirobot systems. This method allows an individual message sending robot to isolate selected message recipient robots based on their spatial location. The recipient robots can then be sent information targeted solely at them, even if the sending robot uses a broadcast communication modality. We demonstrate spatially targeted communication using a heterogeneous multirobot system composed of flying robots and ground-based self-assembling robots. Flying robots use their privileged view of the environment to determine and communicate information to groups of ground-based robots on what morphologies to form to carry out upcoming tasks.
Unmanned Ground Vehicles can be a useful tool to help operators in humanitarian demining. However in many difficult environments autonomous operations are impossible and moreover it can be really difficult to teleoperate the robot from an onboard camera. This work presents an architecture to allow cooperation between a ground robot and a quadrotor UAV. The UAV can autonomously follow the ground robot, by using an image processing algorithm. In this way aerial images are provided that can help trajectory planning in rough environments, via a developed webGIS platform.
We present a unified filtering framework for hybrid metric/topological robot global localization and SLAM. At a high level, our method relies on a topological graph representation whose vertices define uniquely identifiable places in the environment and whose edges define feasible paths between them. At a low level, our method generalizes to any detailed metric submapping technique. The filtering framework we present is designed for multi-hypothesis estimation in order to account for ambiguity when closing loops and to account for uniform uncertainty when initializing pose estimates. Our implementation tests multiple topological hypotheses through the incremental construction of a hypothesis forest with each leaf representing a possible graph/state pair at the current time step. Instead of using a heuristic approach to accept or reject hypotheses, we propose a novel Bayesian method that computes the posterior probability of each hypothesis. In addition, for every topological hypothesis, a metric estimate is maintained with a local Kalman filter. Careful pruning of the hypothesis forest keeps the growing number of hypotheses under control while a garbage-collector hypothesis is used as a catch-all for pruned hypotheses. This enables the filter to recover from unmodeled disturbances such as the kidnapped robot problem.
Assuming that numerical scores are available for the performance of each of n persons on each of n jobs, the "assignment problem" is the quest for an assignment of persons to jobs so that the sum of the n scores so obtained is as large as possible. It is shown that ideas latent in the work of two Hungarian mathematicians may be exploited to yield a new method of solving this problem.
Simultaneous localization, mapping and moving object tracking (SLAMMOT) involves both simultaneous localization and mapping (SLAM) in dynamic en-vironments and detecting and tracking these dynamic objects. In this paper, we establish a mathematical framework to integrate SLAM and moving ob-ject tracking. We describe two solutions: SLAM with generalized objects, and SLAM with detection and tracking of moving objects (DATMO). SLAM with generalized objects calculates a joint posterior over all generalized objects and the robot. Such an approach is similar to existing SLAM algorithms, but with additional structure to allow for motion modeling of generalized objects. Un-fortunately, it is computationally demanding and generally infeasible. SLAM with DATMO decomposes the estimation problem into two separate estima-tors. By maintaining separate posteriors for stationary objects and moving objects, the resulting estimation problems are much lower dimensional then SLAM with generalized objects. Both SLAM and moving object tracking from a moving vehicle in crowded urban areas are daunting tasks. Based on the SLAM with DATMO framework, we propose practical algorithms which deal with issues of perception modeling, data association, and moving object detection. The implementation of SLAM with DATMO was demonstrated us-ing data collected from the CMU Navlab11 vehicle at high speeds in crowded urban environments. Ample experimental results shows the feasibility of the proposed theory and algorithms.
One of the critical components of mapping an unknown environment is the robot's ability to locate itself on a partially explored map. This becomes challenging when the robot experiences positioning error, does not have an external positioning device, nor the luxury of engineered landmarks placed in its free space. This paper presents a new method for simultaneous localization and mapping that exploits the topology of the robot's free space to localize the robot on a partially constructed map. The topology of the environment is encoded in a topological map; the particular topological map used in this paper is the generalized Voronoi graph (GVG), which also encodes some metric information about the robot's environment, as well. In this paper, we present the low-level control laws that generate the GVG edges and nodes, thereby allowing for exploration of an unknown space. With these prescribed control laws, the GVG (or other topological map) can be viewed as an arbitrator for a hybrid control system that determines when to invoke a particular low-level controller from a set of controllers all working toward the high-level capability of mobile robot exploration. The main contribution, however, is using the graph structure of the GVG, via a graph matching process, to localize the robot. Experimental results verify the described work.
In this paper, we present an extended Kalman filter (EKF)-based algorithm for real-time vision-aided inertial navigation. The primary contribution of this work is the derivation of a measurement model that is able to express the geometric constraints that arise when a static feature is observed from multiple camera poses. This measurement model does not require including the 3D feature position in the state vector of the EKF and is optimal, up to linearization errors. The vision-aided inertial navigation algorithm we propose has computational complexity only linear in the number of features, and is capable of high-precision pose estimation in large-scale real-world environments. The performance of the algorithm is demonstrated in extensive experimental results, involving a camera/IMU system localizing within an urban area.
In this paper we describe a system for use on a mobile robot that detects potential loop closures using both visual and spatial appearance of local scenes. Loop closing is the act of correctly asserting that a vehicle has returned to a previously visited location. Current approaches rely heavily on vehicle pose estimates to prompt loop closure. Paradoxically, these approaches are least reliable when the need for accurate loop closure detection is the greatest. Our underlying approach relies instead upon matching distinctive ‘signatures’ of individual local scenes to prompt loop closure. A key advantage of this method is that it is entirely independent of the navigation and or mapping process and so is entirely unaffected by gross errors in pose estimation. Another advantage, which is explored in this paper, is the possibility to enhance robustness of loop closure detection by incorporating heterogeneous sensory observations. We show how a description of local spatial appearance (using laser rangefinder data) can be combined with visual descriptions to form multi-sensory signatures of local scenes which enhance loop-closure detection.
This paper presents a genetic algorithm for solving the problem of structural shape matching. Both sequential and parallel versions of the algorithm have been presented. The genetic operators-reproduction, crossover and mutation-have been constructed for this specific problem. A new variation of the crossover operator, called the color crossover, is presented. This operator has resulted in significant improvement in runtime and algorithm efficiency. Parallelization has been achieved using an “island” model, with several subpopulations and occasional migration. A complete framework for an object recognition system using this genetic algorithm has been presented. Encouraging experimental results have been obtained.
Kuipers, B. and Byun, Y.T., A robot exploration and mapping strategy based on a sematic hierarchy of spatial representations, Robotics and Autonomous System, 8 (1991) 47–63.We have developed a robust qualitative method for robot exploration, mapping, and navigation in large-scale spatial environments. Experiments with a simulated robot in a variety of complex 2D environments have demonstrated that our qualitative method can build an accurate map of a previously unkown environment in spite of substantial random and systematic sensorimotor error.Most current approaches to robot exploration and mapping analyze sensor input to build a geometrically precise map of the environment, then extract topological structure from the geometric description. Our approach recognizes and exploits qualitative properties of large-scale before relatively error-prone geometrical properties. At the control level, distinctive places and distinctive travel edges are identified based on the interaction between the robot's control strategies, its sensorimotor system, and the world. A distinctive place is defined as the local maximum of a distinctiveness measure appropriate to its immediate neighborhood, and is found by a hill-climbing control strategy. A distinctive travel edge, similarly, is defined by a suitable measure and a path-following control strategy. The topological network description is created by linking the distinctive places and travel edges.Metrical information is then incrementally assimilated into localgeometric descriptions of places and edges, and finally merged into a global geometric map. Topological ambiguity arising from sensorily indistinguishable places can be resolved at the topological level by the exploration strategy. With this representation, successful navigation is not critically dependent on the accuracy, or even the existence, of the geometrical description.We present examples demonstrating the process by which the robot explores and builds a map of a complex environment, including the effect of sensory errors. We also discuss new research directions that are suggested by this approach.
A person's cognitive map, or knowledge of large-scale space, is built up from observations gathered as he travels through the environment. It acts as a problem solver to find routes and relative positions, as well as describing the current location. The TOUR model captures the multiple representations that make up the cognitive map, the problem-solving strategies it uses, and the mechanisms for assimilating new information. The representations have rich collections of states of partial knowledge, which support many of the performance characteristics of common-sense knowledge.
In this paper, we propose a robust and fast active contour based method to free space detection in omnidirectional images where the problem of falsely detected obstacles is solved. We define a new functional energy formulation including altitude estimation of keypoints extracted nearby the active contour modeling the free space. The free space, so extracted, could help the robot in real time navigation and environment exploration tasks. To validate the efficiency of the proposed approach, the paper shows comparative results achieved with a classical formulation and our formulation of active contour energies, using images acquired by a robot exploring unknown indoor and outdoor environments, with no prior knowledge of the shape or the extend of the free space.
A robot exploring an unknown environment may need to build a worldmodel from sensor measurements. In order to integrate all the framesof sensor data, it is essential to align the data properly. Anincremental approach has been typically used in the past, in whicheach local frame of data is aligned to a cumulative global model, andthen merged to the model. Because different parts of the model areupdated independently while there are errors in the registration,such an approach may result in an inconsistent model.In this paper, we study the problem of consistent registration ofmultiple frames of measurements (range scans), together with therelated issues of representation and manipulation of spatialuncertainties. Our approach is to maintain all the local frames ofdata as well as the relative spatial relationships between localframes. These spatial relationships are modeled as random variablesand are derived from matching pairwise scans or from odometry. Thenwe formulate a procedure based on the maximum likelihood criterion tooptimally combine all the spatial relations. Consistency is achievedby using all the spatial relations as constraints to solve for thedata frame poses simultaneously. Experiments with both simulated andreal data will be presented.
When multiple robots cooperatively explore an environment, maps from individual robots must be merged to produce a single globally consistent map. This is a challenging problem when the robots do not have a common reference frame or global positioning. In this paper, we describe an algorithm for merging embedded topological maps. Topological maps provide a concise description of the navigability of an environment, and, with measurements easily collected during exploration, the vertices of the map can be embedded in a metric space. Our algorithm uses both the structure and the geometry of topological maps to determine the best correspondence between maps with single or multiple overlapping regions. Experiments with simulated and real-world data demonstrate the efficacy of our algorithm.
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2004. Page 127 blank. Includes bibliographical references (p. 123-126). As robots become ubiquitous, multiple robots dedicated to a single task will become commonplace. Groups of robots can solve problems in fundamentally different ways than individuals while achieving higher levels of performance, but present unique challenges for programming and coordination. This work presents a set of communication techniques and a library of behaviors useful for programming large groups, or swarms, of robots to work together. The gradient-flood communications algorithms presented are resilient to the constantly changing network topology of the Swarm. They provide real-time information that is used to communicate data and to guide robots around the physical environment. Special attention is paid to ensure orderly removal of messages. Decomposing swarm actions into individual behaviors is a daunting task. Complex and subtle local interactions among individuals produce global behaviors, sometimes unexpectedly so. The behavior library presented provides group behavior "building blocks" that interact in predictable manner and can be combined to build complex applications. The underlying distributed algorithms are scaleable, robust, and self-stabilizing. The library of behaviors is designed with an eye towards practical applications, such as exploration, searching, and coordinated motion. All algorithms have been developed and tested on a swarm of 100 physical robots. Data is presented on algorithm correctness and efficiency. stabilizing. The library of behaviors is designed with an eye towards practical applications, such as exploration, searching, and coordinated motion. All algorithms have been developed and tested on a swarm of 100 physical robots. Data is presented on algorithm correctness and efficiency. by James D. McLurkin. S.M.