Simultaneous Localization And Mapping Framework Research Articles

SOF-SLAM: A Semantic Visual SLAM for Dynamic Environments

Simultaneous Localization and Mapping (SLAM) plays an important role in the computer vision and robotics field. The traditional SLAM framework adopts a strong static world assumption for analysis convenience. How to cope with dynamic environments is of vital importance and attracts more attentions. Existing SLAM systems toward dynamic scenes either solely utilize semantic information, solely utilize geometry information, or naively combine the results from them in a loosely coupled way. In this paper, we present SOF-SLAM: Semantic Optical Flow SLAM, a visual semantic SLAM system toward dynamic environments, which is built on RGB-D mode of ORB-SLAM2. A new dynamic features detection approach called semantic optical flow is proposed, which is a kind of tightly coupled way and can fully take advantage of feature's dynamic characteristic hidden in semantic and geometry information to remove dynamic features effectively and reasonably. The pixel-wise semantic segmentation results generated by SegNet serve as mask in the proposed semantic optical flow to get a reliable fundamental matrix, which is then used to filter out the truly dynamic features. Only the remaining static features are reserved in the tracking and optimization module to achieve accurate camera pose estimation in dynamic environments. Experiments on public TUM RGB-D dataset and in real-world environment are conducted. Compared with ORB-SLAM2, the proposed SOF-SLAM achieves averagely 96.73% improvements in high-dynamic scenarios. It also outperforms the other four state-of-the-art SLAM systems which cope with the dynamic environments.

A Novel Feedback Mechanism-Based Stereo Visual-Inertial SLAM

Simultaneous Localization and Mapping (SLAM) combining visual and inertial measurements has achieved significant attention in the community of Robotics and Computer Vision. However, it is still a challenge to balance real-time requirements and accuracy. Therefore, this paper proposes a feedback mechanism for stereo Visual-Inertial SLAM (VISLAM) to provide accurate and real-time motion estimation and map reconstruction. The key idea of the feedback mechanism is that the frontend and backend in the VISLAM system can promote each other. The results of the backend optimization are fed back to the Kalman Filter (KF)-based frontend to reduce the motion estimate error caused by the well-known linearization of the KF estimator. Conversely, this more accurate motion estimate of the frontend can accelerate the backend optimization since it provides a more accurate initial state for the backend. In addition, we design a relocalization and continued SLAM framework with the feedback mechanism for the application of autonomous robot navigation or continuing SLAM. We evaluated the performance of the proposed VISLAM system through experiments on public EuRoC dataset and real-world environments. The experimental results demonstrate that our system is a promising VISLAM system compared with other state-of-the-art VISLAM systems in terms of both computing cost and accuracy.

CCM‐SLAM: Robust and efficient centralized collaborative monocular simultaneous localization and mapping for robotic teams

AbstractRobotic collaboration promises increased robustness and efficiency of missions with great potential in applications, such as search‐and‐rescue and agriculture. Multiagent collaborative simultaneous localization and mapping (SLAM) is right at the core of enabling collaboration, such that each agent can colocalize in and build a map of the workspace. The key challenges at the heart of this problem, however, lie with robust communication, efficient data management, and effective sharing of information among the agents. To this end, here we present CCM‐SLAM, a centralized collaborative SLAM framework for robotic agents, each equipped with a monocular camera, a communication unit, and a small processing board. With each agent able to run visual odometry onboard, CCM‐SLAM ensures their autonomy as individuals, while a central server with potentially bigger computational capacity enables their collaboration by collecting all their experiences, merging and optimizing their maps, or disseminating information back to them, where appropriate. An in‐depth analysis on benchmarking datasets addresses the scalability and the robustness of CCM‐SLAM to information loss and communication delays commonly occurring during real missions. This reveals that in the worst case of communication loss, collaboration is affected, but not the autonomy of the agents. Finally, the practicality of the proposed framework is demonstrated with real flights of three small aircraft equipped with different sensors and computational capabilities onboard and a standard laptop as the server, collaboratively estimating their poses and the scene on the fly.

Dynamic adaptive simultaneous localization and mapping technique for scene change

How to make simultaneous localization and mapping (SLAM) system to be robust and reliable in complex application scenarios has been widely regarded as a key part of automatic and practical robots. Robustness of SLAM system is one of the research focuses in SLAM field. To tackle this issue, we present multi-scene SLAM technique in this paper, which is a novel extensible SLAM framework by combing different SLAM systems facilitated by a scene detection method. Firstly, we propose a robust and extensible SLAM framework called SceneSLAM to enhance the self-adaptive performance of current SLAM systems. By model structure design, it is easy to utilize open-source SLAM systems to be SLAM models of SceneSLAM and modify the scene detection models to support complex application scenarios. Based on the scene detection results, it can schedule the SLAM models automatically. Secondly, aiming at indoor, outdoor and dark scene detection problems, we present a scene detection model based on convolutional neural network and Bias filter optimization. Experimental results show that the proposed scene detection model has reliable accuracy and stability in detecting indoor, outdoor and dark scenes. What’s more, considering sensor failure in indoor, outdoor and dark scenes, we design dynamic adaptive SLAM models to handle the issue. Map fusion is performed to achieve globally consistent localization and mapping when SLAM models scheduled. At last but not least, we build up a prototype system based on SceneSLAM to enhance the reliability of existing SLAM systems when the scene changes between indoor, outdoor and dark scenes. This system runs on a TurtleBot robot equipped with a Kinect sensor. The experimental results show that multi-scene SLAM technique proposed in this paper provides an effective solution to enhance the robustness of existing SLAM systems in dynamic environments.

H-SLAM: Rao-Blackwellized Particle Filter SLAM Using Hilbert Maps.

Occupancy Grid maps provide a probabilistic representation of space which is important for a variety of robotic applications like path planning and autonomous manipulation. In this paper, a SLAM (Simultaneous Localization and Mapping) framework capable of obtaining this representation online is presented. The H-SLAM (Hilbert Maps SLAM) is based on Hilbert Map representation and uses a Particle Filter to represent the robot state. Hilbert Maps offer a continuous probabilistic representation with a small memory footprint. We present a series of experimental results carried both in simulation and with real AUVs (Autonomous Underwater Vehicles). These results demonstrate that our approach is able to represent the environment more consistently while capable of running online.

DRIFT-FREE INDOOR NAVIGATION USING SIMULTANEOUS LOCALIZATION AND MAPPING OF THE AMBIENT HETEROGENEOUS MAGNETIC FIELD

Abstract. In the absence of external reference position information (e.g. surveyed targets or Global Navigation Satellite Systems) Simultaneous Localization and Mapping (SLAM) has proven to be an effective method for indoor navigation. The positioning drift can be reduced with regular loop-closures and global relaxation as the backend, thus achieving a good balance between exploration and exploitation. Although vision-based systems like laser scanners are typically deployed for SLAM, these sensors are heavy, energy inefficient, and expensive, making them unattractive for wearables or smartphone applications. However, the concept of SLAM can be extended to non-optical systems such as magnetometers. Instead of matching features such as walls and furniture using some variation of the Iterative Closest Point algorithm, the local magnetic field can be matched to provide loop-closure and global trajectory updates in a Gaussian Process (GP) SLAM framework. With a MEMS-based inertial measurement unit providing a continuous trajectory, and the matching of locally distinct magnetic field maps, experimental results in this paper show that a drift-free navigation solution in an indoor environment with millimetre-level accuracy can be achieved. The GP-SLAM approach presented can be formulated as a maximum a posteriori estimation problem and it can naturally perform loop-detection, feature-to-feature distance minimization, global trajectory optimization, and magnetic field map estimation simultaneously. Spatially continuous features (i.e. smooth magnetic field signatures) are used instead of discrete feature correspondences (e.g. point-to-point) as in conventional vision-based SLAM. These position updates from the ambient magnetic field also provide enough information for calibrating the accelerometer bias and gyroscope bias in-use. The only restriction for this method is the need for magnetic disturbances (which is typically not an issue for indoor environments); however, no assumptions are required for the general motion of the sensor (e.g. static periods).

SLAM++ 1 -A highly efficient and temporally scalable incremental SLAM framework

The most common way to deal with the uncertainty present in noisy sensorial perception and action is to model the problem with a probabilistic framework. Maximum likelihood estimation is a well-known estimation method used in many robotic and computer vision applications. Under Gaussian assumption, the maximum likelihood estimation converts to a nonlinear least squares problem. Efficient solutions to nonlinear least squares exist and they are based on iteratively solving sparse linear systems until convergence. In general, the existing solutions provide only an estimation of the mean state vector, the resulting covariance being computationally too expensive to recover. Nevertheless, in many simultaneous localization and mapping (SLAM) applications, knowing only the mean vector is not enough. Data association, obtaining reduced state representations, active decisions and next best view are only a few of the applications that require fast state covariance recovery. Furthermore, computer vision and robotic applications are in general performed online. In this case, the state is updated and recomputed every step and its size is continuously growing, therefore, the estimation process may become highly computationally demanding. This paper introduces a general framework for incremental maximum likelihood estimation called SLAM++, which fully benefits from the incremental nature of the online applications, and provides efficient estimation of both the mean and the covariance of the estimate. Based on that, we propose a strategy for maintaining a sparse and scalable state representation for large scale mapping, which uses information theory measures to integrate only informative and non-redundant contributions to the state representation. SLAM++ differs from existing implementations by performing all the matrix operations by blocks. This led to extremely fast matrix manipulation and arithmetic operations used in nonlinear least squares. Even though this paper tests SLAM++ efficiency on SLAM problems, its applicability remains general.

Accurate Mobile Urban Mapping via Digital Map-Based SLAM.

This paper presents accurate urban map generation using digital map-based Simultaneous Localization and Mapping (SLAM). Throughout this work, our main objective is generating a 3D and lane map aiming for sub-meter accuracy. In conventional mapping approaches, achieving extremely high accuracy was performed by either (i) exploiting costly airborne sensors or (ii) surveying with a static mapping system in a stationary platform. Mobile scanning systems recently have gathered popularity but are mostly limited by the availability of the Global Positioning System (GPS). We focus on the fact that the availability of GPS and urban structures are both sporadic but complementary. By modeling both GPS and digital map data as measurements and integrating them with other sensor measurements, we leverage SLAM for an accurate mobile mapping system. Our proposed algorithm generates an efficient graph SLAM and achieves a framework running in real-time and targeting sub-meter accuracy with a mobile platform. Integrated with the SLAM framework, we implement a motion-adaptive model for the Inverse Perspective Mapping (IPM). Using motion estimation derived from SLAM, the experimental results show that the proposed approaches provide stable bird’s-eye view images, even with significant motion during the drive. Our real-time map generation framework is validated via a long-distance urban test and evaluated at randomly sampled points using Real-Time Kinematic (RTK)-GPS.

Multibeam 3D Underwater SLAM with Probabilistic Registration.

This paper describes a pose-based underwater 3D Simultaneous Localization and Mapping (SLAM) using a multibeam echosounder to produce high consistency underwater maps. The proposed algorithm compounds swath profiles of the seafloor with dead reckoning localization to build surface patches (i.e., point clouds). An Iterative Closest Point (ICP) with a probabilistic implementation is then used to register the point clouds, taking into account their uncertainties. The registration process is divided in two steps: (1) point-to-point association for coarse registration and (2) point-to-plane association for fine registration. The point clouds of the surfaces to be registered are sub-sampled in order to decrease both the computation time and also the potential of falling into local minima during the registration. In addition, a heuristic is used to decrease the complexity of the association step of the ICP from to . The performance of the SLAM framework is tested using two real world datasets: First, a 2.5D bathymetric dataset obtained with the usual down-looking multibeam sonar configuration, and second, a full 3D underwater dataset acquired with a multibeam sonar mounted on a pan and tilt unit.

국소 집단 최적화 기법을 적용한 비정형 해저면 환경에서의 비주얼 SLAM

As computer vision algorithms are developed on a continuous basis, the visual information from vision sensors has been widely used in the context of simultaneous localization and mapping (SLAM), called visual SLAM, which utilizes relative motion information between images. This research addresses a visual SLAM framework for online localization and mapping in an unstructured seabed environment that can be applied to a low-cost unmanned underwater vehicle equipped with a single monocular camera as a major measurement sensor. Typically, an image motion model with a predefined dimensionality can be corrupted by errors due to the violation of the model assumptions, which may lead to performance degradation of the visual SLAM estimation. To deal with the erroneous image motion model, this study employs a local bundle optimization (LBO) scheme when a closed loop is detected. The results of comparison between visual SLAM estimation with LBO and the other case are presented to validate the effectiveness of the proposed methodology.

Rao-Blackwellized visual SLAM for small UAVs with vehicle model partition

Purpose – The purpose of this paper is to present a Rao–Blackwellized particle filter (RBPF) approach for the visual simultaneous localization and mapping (SLAM) of small unmanned aerial vehicles (UAVs). Design/methodology/approach – Measurements from inertial measurement unit, barometric altimeter and monocular camera are fused to estimate the state of the vehicle while building a feature map. In this SLAM framework, an extra factorization method is proposed to partition the vehicle model into subspaces as the internal and external states. The internal state is estimated by an extended Kalman filter (EKF). A particle filter is employed for the external state estimation and parallel EKFs are for the map management. Findings – Simulation results indicate that the proposed approach is more stable and accurate than other existing marginalized particle filter-based SLAM algorithms. Experiments are also carried out to verify the effectiveness of this SLAM method by comparing with a referential global positioning system/inertial navigation system. Originality/value – The main contribution of this paper is the theoretical derivation and experimental application of the Rao–Blackwellized visual SLAM algorithm with vehicle model partition for small UAVs.

Embedded Visual SLAM: Applications for Low-Cost Consumer Robots

A camera poses a highly attractive choice as a sensor in implementing simultaneous localization and mapping (SLAM) for low-cost consumer robots such as home cleaning robots. This is due to its low cost, light weight, and low power consumption. However, most of the visual SLAMs available to date are not designed and, consequently, not suitable for use in a low-cost embedded SLAM for consumer robots. This article presents a computationally light yet performance-wise robust SLAM algorithm and its implementation as an embedded system for low-cost consumer robots using an upward-looking camera. Especially for a large-scale mapping of indoor environments, methods of pose graph optimization as well as submapping are employed. An occupancy grid map is used to integrate an efficient Kalman filter-based localization into a SLAM framework. Furthermore, an algorithmic visual compass is introduced as a means of reducing the computational complexity involved in pose graph optimization, taking advantage of the distinct geometric features of the scenes captured by an upward-looking camera. The proposed visual SLAM is implemented in a real home cleaning robot as an embedded system using an ARM11 processor. Extensive test results demonstrate the power of the proposed embedded visual SLAM in terms of not only its computational efficiency but also its performance robustness in realworld applications.

Using Embodied Data for Localization and Mapping

Mobile autonomous robots have finally emerged from the confined spaces of structured and controlled indoor environments. To fulfill the promises of ubiquitous robotics in unstructured outdoor environments, robust navigation is a key requirement. The research in the simultaneous localization and mapping (SLAM) community has largely focused on optical sensors to solve this problem, and the fact that the robot is a physical entity has largely been ignored. In this paper, a hierarchical SLAM framework is proposed that takes the interaction of the robot with the environment into account. A sequential Monte Carlo filter is used to generate local map segments with a combination of visual and embodied data associations. Constraints between segments are used to generate globally consistent maps with a focus on suitability for navigation tasks. The proposed method is experimentally verified on two different outdoor robots. The results show that the approach is viable and that the rich modeling of the robot with its environment provides a new modality with the potential for improving existing visual methods and extending the availability of SLAM in domains where visual processing alone is not sufficient.

Map Matching and Data Association for Large-Scale Two-dimensional Laser Scan-based SLAM

Reliable data association techniques for simultaneous localization and mapping (SLAM) are necessary for the generation of large-scale maps in unstructured outdoor environments. Data association techniques are required at two levels: the local level represents the inner loop of the mapping algorithm, and the global level where newly mapped areas are matched to previously mapped areas to detect repeated coverage and close loops. Local map building is achieved using a robust iterative scan matching technique incorporated into an extended Kalman filter where the state consists of the current pose and previous poses sampled periodically and at a fixed lag from the current time. The introduction of states at a fixed time lag significantly reduces the growth of errors in the location estimate and the resultant map. For global matching, we enhance existing histogram cross-correlation techniques, introducing entropy sequences of projection histograms and an exhaustive correlation approach for reliable matching in unstructured environments. This enables loop closure without depending on prior knowledge of map alignment. These data association techniques are incorporated into the Atlas SLAM framework, enabling the generation of accurate two-dimensional laser maps over tens of kilometers in challenging outdoor environments.

A Virtual Range Finder based on Monocular Vision System in Simultaneous Localization and Mapping

This paper presents a virtual range finder model with the monocular vision system for simultaneous localization and mapping (SLAM). It relaxes the constraint often cited in the literature that the motion of the optical axis has to be parallel, and reduces the errors for range extraction by a single camera. This model could also provide a supplementary range measurement for landmark initialization in bearing-only SLAM. As the sensor data transformation from pixel to metric value is a nonlinear process, the uncertainty for observation model adopted in Extended Kalman Filter (EKF) SLAM framework can not be in the Gaussian form, which probably makes difficult for data association and SLAM. Concerning this problem, we present a new data association technique based on the homography transformation by a sequence of images and integrate it into the update process of the EKF to assist the innovation computation. The experimental results on real data validated the performance of the virtual range finder model and the new data association approach.