Structured Indoor Environments Research Articles

GRID-FAST: A Grid-based Intersection Detection for Fast Semantic Topometric Mapping

This article introduces a novel approach to constructing a topometric map that allows for efficient navigation and decision-making in mobile robotics applications. The method generates the topometric map from a 2D grid-based map. The topometric map segments areas of the input map into different structural-semantic classes: intersections, pathways, dead ends, and pathways leading to unexplored areas. This method is grounded in a new technique for intersection detection that identifies the area and the openings of intersections in a semantically meaningful way. The framework introduces two levels of pre-filtering with minimal computational cost to eliminate small openings and objects from the map which are unimportant in the context of high-level map segmentation and decision making. The topological map generated by GRID-FAST enables fast navigation in large-scale environments, and the structural semantics can aid in mission planning, autonomous exploration, and human-to-robot cooperation. The efficacy of the proposed method is demonstrated through validation on real maps gathered from robotic experiments: 1) a structured indoor environment, 2) an unstructured cave-like subterranean environment, and 3) a large-scale outdoor environment, which comprises pathways, buildings, and scattered objects. Additionally, the proposed framework has been compared with state-of-the-art topological mapping solutions and is able to produce a topometric and topological map with up to 92% fewer nodes than the next best solution. The method proposed in this article has been implemented in the robotics framework ROS and is open-sourced. The code is available at: https://github.com/LTU-RAI/GRID-FAST.

Multi-Level Indoor Path Planning and Clearance-Based Path Optimization for Search and Rescue Operations

In this study a multi-level path planning system is proposed for indoor search and rescue operations. Requirements for the path planning system are derived based on the operational concept of the integrated indoor navigation system. Different aspects of various path planning algorithms are assessed, and their suitability to search and rescue operations in structured indoor environments is investigated. A five-step path planning system is proposed, which consists of map pre-processing, segment path planning, graph processing, route optimization, and path post-processing. The proposed method addresses a multi-goal path planning problem in a multi-story building in a computationally efficient way by adopting a graph-based approach while satisfying such requirements as clearance conditions in the pre- and post-processing steps. Furthermore, a multi-query approach is adopted to exploit the response time and earn flexibility with respect to environmental changes. The effectiveness of the proposed path planning system is demonstrated through numerical simulations.

Situational Graphs for Robot Navigation in Structured Indoor Environments

Mobile robots should be aware of their <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">situation</i> , comprising the deep understanding of their surrounding environment along with the estimation of its own state, to successfully make intelligent decisions and execute tasks autonomously in real environments. 3D scene graphs are an emerging field of research that propose to represent the environment in a joint model comprising geometric, semantic and relational/topological dimensions. Although 3D scene graphs have already been combined with SLAM techniques to provide robots with situational understanding, further research is still required to effectively deploy them on-board mobile robots. To this end, we present in this paper a novel, real-time, online built Situational Graph ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S-Graph</i> ), which combines in a single optimizable graph, the representation of the environment with the aforementioned three dimensions, together with the robot pose. Our method utilizes odometry readings and planar surfaces extracted from 3D LiDAR scans, to construct and optimize in real-time a three layered <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S-Graph</i> that includes (1) a robot tracking layer where the robot poses are registered, (2) a metric-semantic layer with features such as planar walls and (3) our novel topological layer constraining the planar walls using higher-level features such as corridors and rooms. Our proposal does not only demonstrate state-of-the-art results for pose estimation of the robot, but also contributes with a metric-semantic-topological model of the environment.

A new monocular vision simultaneous localization and mapping process for high-precision positioning in structured indoor environments

High-precision positioning in areas with unobtrusive features is difficult to achieve with visual based indoor positioning solutions. Most current solutions offer low precision and are expensive and/or require a priori training. A ceiling distributed on the same plane is regularly arranged and widespread in structured indoor environments. We propose a new monocular vision simultaneous localization and mapping (NMV SLAM) method for high-precision indoor positioning. First, image morphology technology is adopted to extract the ceiling corner accurately. Second, the geometric solution based on the a priori ceiling map realizes global positioning and makes up for the deficiency of time-consuming nonlinear optimization. Experiments show that the root mean square error of position measured by the proposed NMV SLAM process is less than 5.43 mm in a room with an entire ceiling. Moreover, the proposed NMV SLAM processes an average of 30.61 frames in 1 s on an i5-9400F central processing unit.

Real-Time 2-D Lidar Odometry Based on ICP

This study presents a 2-D lidar odometry based on an ICP (iterative closest point) variant used in a simple and straightforward platform that achieves real-time and low-drift performance. With a designated multi-scale feature extraction procedure, the lidar cloud information can be utilized at multiple levels and the speed of data association can be accelerated according to the multi-scale data structure, thereby achieving robust feature extraction and fast scan-matching algorithms. First, on a large scale, the lidar point cloud data are classified according to the curvature into two parts: smooth collection and rough collection. Then, on a small scale, noise and unstable points in the smooth or rough collection are filtered, and edge points and corner points are extracted. Then, the proposed tangent-vector-pairs based on edge and corner points are applied to evaluate the rotation term, which is significant for producing a stable solution in motion estimation. We compare our performance with two excellent open-source SLAM algorithms, Cartographer and Hector SLAM, using collected and open-access datasets in structured indoor environments. The results indicate that our method can achieve better accuracy.

Autonomous and Safe Navigation of Mobile Robots in Vineyard with Smooth Collision Avoidance

In recent years, autonomous robots have extensively been used to automate several vineyard tasks. Autonomous navigation is an indispensable component of such field robots. Autonomous and safe navigation has been well studied in indoor environments and many algorithms have been proposed. However, unlike structured indoor environments, vineyards pose special challenges for robot navigation. Particularly, safe robot navigation is crucial to avoid damaging the grapes. In this regard, we propose an algorithm that enables autonomous and safe robot navigation in vineyards. The proposed algorithm relies on data from a Lidar sensor and does not require a GPS. In addition, the proposed algorithm can avoid dynamic obstacles in the vineyard while smoothing the robot’s trajectories. The curvature of the trajectories can be controlled, keeping a safe distance from both the crop and the dynamic obstacles. We have tested the algorithm in both a simulation and with robots in an actual vineyard. The results show that the robot can safely navigate the lanes of the vineyard and smoothly avoid dynamic obstacles such as moving people without abruptly stopping or executing sharp turns. The algorithm performs in real-time and can easily be integrated into robots deployed in vineyards.

Depth-Image Segmentation Based on Evolving Principles for 3D Sensing of Structured Indoor Environments.

This paper presents an approach of depth image segmentation based on the Evolving Principal Component Clustering (EPCC) method, which exploits data locality in an ordered data stream. The parameters of linear prototypes, which are used to describe different clusters, are estimated in a recursive manner. The main contribution of this work is the extension and application of the EPCC to 3D space for recursive and real-time detection of flat connected surfaces based on linear segments, which are all detected in an evolving way. To obtain optimal results when processing homogeneous surfaces, we introduced two-step filtering for outlier detection within a clustering framework and considered the noise model, which allowed for the compensation of characteristic uncertainties that are introduced into the measurements of depth sensors. The developed algorithm was compared with well-known methods for point cloud segmentation. The proposed approach achieves better segmentation results over longer distances for which the signal-to-noise ratio is low, without prior filtering of the data. On the given database, an average rate higher than 90% was obtained for successfully detected flat surfaces, which indicates high performance when processing huge point clouds in a non-iterative manner.

Laser-Based Intersection-Aware Human Following With a Mobile Robot in Indoor Environments

Human following in structured indoor environments has to face the challenge of full occlusion caused by the walls when the target person makes a turn at the corridor intersections. This may result in short-term, and even permanent loss of the target from the field of view of the robot. In this paper, human following with a mobile robot in presence of potential occlusions occurring at corridor intersections is addressed. The robot detects four different types of corridor intersections using the on-board laser scanner. Then, a potential-field-based human tracker is designed by integrating the intersection information into the potential function, in order to increase the visibility of the target, while maintaining the relative distance and orientation between the target and the robot. Simultaneously, the robot builds a multihypothesis topological map of the environment based on an improved generalized Voronoi graph, where the edges represent the corridors and the vertices are the virtual meet points extracted from the intersections. In such a way, simultaneous human following and topological mapping are achieved. Simulation and experimental results show that the proposed method can largely avoid occlusion of the target and obtain good performance of human following and topological mapping.

Control of quadrotor trajectory tracking with sliding mode control optimized by neural networks

Quadrotor or unmanned helicopter is a mobile robot which often flies in unknown environment to perform special missions. In navigational tasks, the robot is intended to fly autonomously toward a target position by following an optimum trajectory. For a successful navigation, controlled attitude, minimum position and velocity error and obstacles collision avoidance are often considered during trajectory tracking procedure. By considering environmental variabilities and due to the existence of noises, uncertainties and unpredictable factors, it is indispensable to steer and control moving robots using sophisticated autonomous algorithms. In this work, a nonlinear model of four-rotor helicopter is simulated. An optimized terminal sliding mode control is then designed to control trajectory tracking. In order to improve the time indices for sliding mode controller, this controller is modified with neural networks. The idea is to optimize the controller parameters through a network learning process which is based on the control process error. The proposed method is evaluated with simulated and real-world indoor navigation tasks. Trajectories that are tracked by quadrotor are generated by a simultaneous localization and mapping algorithm and refined with an optimization technique. A well-known simultaneous localization and mapping technique (a camera-based extended Kalman filter-simultaneous localization and mapping) is employed to generate maps, and a path planning algorithm (particle swarm optimization) is utilized to optimize a collision-free flight path using the probability-based maps generated by simultaneous localization and mapping. Simulations and experiment are done in unknown but structured indoor environments containing a number of obstacles. The steady state error, the reaching and settle time and the chattering effect are all quantified and assessed. The controlled experimental flight robustness and sensitivity are further verified for noises occurred on vision and data acquisition system. Results indicate suitable performance for the proposed neural network-sliding mode controller. Less error and more stability were achieved comparative to the conventional sliding mode controllers.

State‐of‐the‐art in Automatic 3D Reconstruction of Structured Indoor Environments

AbstractCreating high‐level structured 3D models of real‐world indoor scenes from captured data is a fundamental task which has important applications in many fields. Given the complexity and variability of interior environments and the need to cope with noisy and partial captured data, many open research problems remain, despite the substantial progress made in the past decade. In this survey, we provide an up‐to‐date integrative view of the field, bridging complementary views coming from computer graphics and computer vision. After providing a characterization of input sources, we define the structure of output models and the priors exploited to bridge the gap between imperfect sources and desired output. We then identify and discuss the main components of a structured reconstruction pipeline, and review how they are combined in scalable solutions working at the building level. We finally point out relevant research issues and analyze research trends.

Improved mobile robot based gas distribution mapping through propagated distance transform for structured indoor environment

ABSTRACTMobile robot carrying gas sensors have been widely used in mobile olfaction applications. One of the challenging tasks in this research field is Gas Distribution Mapping (GDM). GDM is a representation of how volatile organic compound is spatially dispersed within an environment. This paper addresses the effect of obstacles towards GDM for indoor environment. This work proposes a solution by improvising the Kernel DM + V technique using propagated distance transform (DT) as the weighing function. Since DT computations are CPU heavy, parallel computing, using Compute Unified Device Architecture (CUDA) available in Graphics Processing Unit (GPU), is used to accelerate the DT computation. The proposed solution is compared with the Kernel DM + V algorithm, presenting that the proposed method drastically improves the quality of GDM under various kernel sizes. The study is also further extended towards the effect of obstacles on gas source localization task. The outcome of this work proves that the proposed method shows better accuracy for GDM estimation and gas source localization if obstacle information is considered.

A Novel Position and Orientation Sensor for Indoor Navigation Based on Linear CCDs.

The position and orientation of a mobile agent, such as robot or drone, etc., should be estimated in a timely way during operation in the structured indoor environment, so as to ensure the security and efficiency of task execution. Concerning the problem that the position and orientation are often estimated separately by different kinds of sensors in the off-the-shelf methods, we design a novel position orientation sensor (POS). The POS consists of four pairs of linear charge-coupled devices (CCDs) and cylindrical lenses, which can estimate the 3D coordinate of the anchor in the POS’s field of view. After detecting at least three anchors in its field of vision sequentially, the Rodrigues coordinate transformation algorithm is utilized to estimate the position and orientation of POS simultaneously. Meanwhile, the position and orientation are estimated at the receiver side. Hence there is no privacy concern associated with this system. The architecture of the proposed POS is symmetrical and redundant, even if one of the linear CCDs or cylindrical lens malfunctions, the whole system could still work normally. The proposed method is cost-effective and easily extends to a wide range. The numerical simulation demonstrates the feasibility and high accuracy of the proposed method, and it outperforms the off-the-shelf methods.

Bayesian Mapping-Based Autonomous Exploration and Patrol of 3D Structured Indoor Environments with Multiple Flying Robots

Mobile robots are frequently faced with mapping and exploring uncertain environments in surveillance, military, and convenience tasks. Often times, human teleoperation is either inconvenient or infeasible for these kinds missions. Furthermore, these tasks can be improved by cooperative multi-agent systems, where coordinating robotic efforts can be complicated and computationally-expensive. This paper presents a stochastic framework for autonomous exploration and patrol with multiple cooperating robots. The first contribution extends the authors’ prior work in single-robot exact occupancy grid mapping and autonomous exploration in a 2D environment to mapping and exploring in a 3D environment. The proposed 3D occupancy grid map is computed efficiently using an inverse sensor model that accounts for the sensor uncertainty, where we propose how several measurement sources may be fused together by considering depth readings individually. This approach is scalable to larger and more complex scenarios for real-time mapping. Furthermore, this paper shows how important aspects of a 3D map representing a structured environment are projected onto a 2D occupancy grid map, where an autonomous exploration algorithm is designed to select robotic motions that maximize map information gain. The mapping and exploration algorithms are demonstrated with an experiment where a quadrotor autonomously maps and explores an initially-uncertain environment. The second contribution is a novel approach to multi-vehicle cooperative patrol of environments based on map uncertainty. We propose a cooperative autonomous exploration algorithm, which applies a bidding-based framework to coordinate robotic efforts for improving occupancy grid map information gain. Since these exploration approaches are based on probabilistic knowledge about the map, the 3D occupancy grid map is systematically degraded over time to encourage the robots to revisit regions as time passes, thereby patrolling the environment. Furthermore, using a Bayesian framework and receding horizons, the algorithm is robust to dynamic obstacles within the mapping space. The efficacy of the proposed multi-vehicle cooperative patrol is illustrated with a simulation involving three robots patrolling a large floor plan with a non-cooperative person walking around the space.

A Semantic-Based Gas Source Localization with a Mobile Robot Combining Vision and Chemical Sensing.

This paper addresses the localization of a gas emission source within a real-world human environment with a mobile robot. Our approach is based on an efficient and coherent system that fuses different sensor modalities (i.e., vision and chemical sensing) to exploit, for the first time, the semantic relationships among the detected gases and the objects visually recognized in the environment. This novel approach allows the robot to focus the search on a finite set of potential gas source candidates (dynamically updated as the robot operates), while accounting for the non-negligible uncertainties in the object recognition and gas classification tasks involved in the process. This approach is particularly interesting for structured indoor environments containing multiple obstacles and objects, enabling the inference of the relations between objects and between objects and gases. A probabilistic Bayesian framework is proposed to handle all these uncertainties and semantic relations, providing an ordered list of candidates to be the source. This candidate list is updated dynamically upon new sensor measurements to account for objects not previously considered in the search process. The exploitation of such probabilities together with information such as the locations of the objects, or the time needed to validate whether a given candidate is truly releasing gases, is delegated to a path planning algorithm based on Markov decision processes to minimize the search time. The system was tested in an office-like scenario, both with simulated and real experiments, to enable the comparison of different path planning strategies and to validate its efficiency under real-world conditions.

Appearance-Based Indoor Navigation by IBVS Using Line Segments

This letter presents a method for image-based navigation from an image memory using line segments as landmarks. The entire navigation process is based on 2-D image information without using any 3-D information at all. The environment is represented by a set of reference images with overlapping landmarks, which are acquired during a prior learning phase. These reference images define the path to follow during the navigation. The switching of reference images is done exploiting the line segment matching between the current acquired image and nearby reference images. Three view matching result is used to compute the rotational velocity of a mobile robot during its navigation by visual servoing. Real-time navigation has been validated inside a corridor and inside a room with a Pioneer 3-DX equipped with an on-board camera. The obtained results confirm the viability of our approach, and verify that accurate mapping and localization are not necessary for a useful indoor navigation as well as that line segments are better features in the structured indoor environment.

Feasible acceleration count: A novel dynamic stability metric and its use in incremental motion planning on uneven terrain

Application of wheeled mobile robots has gradually progressed from the confines of structured indoor environments to rough outdoor terrains. Material transport and exploration are some of the few areas where wheeled robots are required to navigate over uneven terrains. Stable and efficient navigation of wheeled robots over uneven terrains requires a framework which can correctly ascertain the stability and maneuverability for a given robot’s state. Most existing works on uneven terrain navigation assume a one-to-one correspondence between postural stability and maneuverability. In this paper, we show that such characterization is incomplete as states having high postural stability may have restricted maneuverability depending on underlying terrain topology. We thus, present a novel metric called Feasible Acceleration Count (FAC), introduced in our earlier works as a unified measure of robot stability and maneuverability. The metric gives the measure of the space of feasible accelerations available to the robot at a given state. The feasibility is decided by a set of inequalities which depends not only on robot’s state but also on surface normals at the wheel ground contact point. This unique feature of the FAC metric makes it a more appropriate choice for motion planning on uneven terrains than metrics like Tip-Over. We further show that since space of feasible accelerations is a direct characterization of the space of possible motions at a given state, the metric FAC, also quantifies the quality of state space exploration achieved at each step of incremental sampling based planners. We build on top of this aspect of FAC and present an incremental trajectory planner with a novel node selection criteria for navigation of generic four wheeled robots and articulated systems like mobile manipulators on uneven terrain.

A Single Frame Depth Visual Gyroscope and its Integration for Robot Navigation and Mapping in Structured Indoor Environments

An accurate navigation system is an essential and important part for the mobile robot. The recent appearance of low cost RGBD cameras has made 3D point clouds together with RGB information easy acc...

2A2-L06 Mapping Landmarks in Structured Indoor Environments by using RDF data models and SPARQL engine based navigation

2A2-L06 Mapping Landmarks in Structured Indoor Environments by using RDF data models and SPARQL engine based navigation

Matching monocular lightweight features using N-gram techniques for topological location identification

SUMMARYIn SLAM (simultaneous localization and mapping), the topological paradigm provides a more natural and compact solution that scales better with the size of the environment. Computer vision has always been regarded as the ideal sensor technology for topological feature extraction and description and several methods have been proposed in the literature, but they are either time-consuming, require plenty of different sensors, or are very sensitive to perceptual aliasing, all of which limit their application scope.This paper presents a fast-to-compute collection of features extracted from monocular images, and an adaptive matching procedure for location identification in structured indoor environments inspired by the natural language processing field. Although only dominant vertical lines, color histograms, and a reduced number of keypoints are employed in this paper, the matching framework introduced allows for the incorporation of almost any other type of feature. The results of the experiments carried out in a home and an office environment suggest that the proposed method could be used for real-time topological scene recognition even if the environment changes moderately over time. Due to the combination of complementary features, high precision can be achieved within reasonable computation time by using weaker but faster descriptors.

Formula omitted]: Geometrical matching analytical algorithm for fast mobile robots global self-localization

This paper presents a new algorithm for fast mobile robot self-localization in structured indoor environments based on geometrical and analytical matching, GEMA2. The proposed method takes advantage of the available structural information to perform a geometrical matching with the environment information provided by measurements collected by a laser range finder. In contrast to other global self-localization algorithms like Monte Carlo or SLAM, GEMA2 provides a linear cost with respect the number of measures collected, making it suitable for resource-constrained embedded systems. The proposed approach has been implemented and tested in a mobile robot with limited computational resources showing a fast converge from global self-localization.