GPS-denied Indoor Environments Research Articles

Landmark-based distributed topological mapping and navigation in GPS-denied urban environments using teams of low-cost robots

In this paper, we address the problem of autonomous multi-robot mapping, exploration and navigation in unknown, GPS-denied indoor or urban environments using a team of robots equipped with directional sensors with limited sensing capabilities and limited computational resources. The robots have no a priori knowledge of the environment and need to rapidly explore and construct a map in a distributed manner using existing landmarks, the presence of which can be detected using onboard senors, although little to no metric information (distance or bearing to the landmarks) is available. In order to correctly and effectively achieve this, the presence of a necessary density/distribution of landmarks is ensured by design of the urban/indoor environment. We thus address this problem in two phases: (1) During the design/construction of the urban/indoor environment we can ensure that sufficient landmarks are placed within the environment. To that end we develop a filtration-based approach for designing strategic placement of landmarks in an environment. (2) We develop a distributed algorithm which a team of robots, with no a priori knowledge of the environment, can use to explore such an environment, construct a topological map requiring no metric/distance information, and use that map to navigate within the environment. This is achieved using a topological representation of the environment (called a Landmark Complex), instead of constructing a complete metric/pixel map. The representation is built by the robot as well as used by them for navigation through a balanced strategy involving exploration and exploitation. We use tools from homology theory for identifying “holes” in the coverage/exploration of the unknown environment and hence guide the robots towards achieving a complete exploration and mapping of the environment. Our simulation results demonstrate the effectiveness of the proposed metric-free topological (simplicial complex) representation in achieving exploration, localization and navigation within the environment.

Tightly-coupled fusion of iGPS measurements in optimization-based visual SLAM.

The monocular visual Simultaneous Localization and Mapping (SLAM) can achieve accurate and robust pose estimation with excellent perceptual ability. However, accumulated image error over time brings out excessive trajectory drift in a GPS-denied indoor environment lacking global positioning constraints. In this paper, we propose a novel optimization-based SLAM fusing rich visual features and indoor GPS (iGPS) measurements, obtained by workshop Measurement Position System, (wMPS), to tackle the problem of trajectory drift associated with visual SLAM. Here, we first calibrate the spatial shift and temporal offset of two types of sensors using multi-view alignment and pose optimization bundle adjustment (BA) algorithms, respectively. Then, we initialize camera poses and map points in a unified world frame by iGPS-aided monocular initialization and PnP algorithms. Finally, we employ a tightly-coupled fusion of iGPS measurements and visual observations using a pose optimization strategy for high-accuracy global localization and mapping. In experiments, public datasets and self-collected sequences are used to evaluate the performance of our approach. The proposed system improves the result of absolute trajectory error from the current state-of-the-art 19.16mm (ORB-SLAM3) to 5.87mm in the public dataset and from 31.20mm to 5.85mm in the real-world experiment. Furthermore, the proposed system also shows good robustness in the evaluations.

Improved CNN-based Path Planning So an Autonomous UAV Can Climb Stairs By using a LiDAR Sensor

Unmanned aerial vehicles (UAVs) have tremendous potential in civil and public areas. These are especially beneficial in applications where human lives are threatened. Autonomous navigation in unknown environments is a challenging issue for UAVs where decision-based navigation is required. In this paper, a deep learning (DL) approach is presented that aids autonomous navigation for UAVs in completely unknown, GPS-denied indoor environments. The UAV is equipped with a monocular camera and a light detection and ranging (LiDAR) sensor to determine each next maneuver and distance calculation, respectively. For deeper feature extraction, a version of You Only Look Once (YOLOv3-tiny) is improved by adding a convolution layer with different filter sizes. The process is observed as an exercise where the DL model classifies the targeted image as stairs or not stairs. We created our dataset considering the indoor scenario for specific implementation. Comprehensive experimental results are compared with YOLOv3-tiny, indicating better performance in terms of accuracy, recall, F1-score, precision, and maneuvering movements.

A Tightly Coupled VLC-Inertial Localization System by EKF

Lightweight global localization is favorable by many resource-constrained platforms working in GPS-denied indoor environments, such as service robots and mobile devices. In recent years, visible light communication (VLC) has emerged as a promising technology that can support global positioning in buildings by reusing the widespread LED luminaries as artificial visual landmarks. In this letter, we propose a novel VLC/IMU integrated system with a tightly coupled formulation by an extended-Kalman filter (EKF) for robust VLC-inertial localization. By tightly fusing the inertial measurements with the visual measurements of LED fiducials, our EKF localizer can provide lightweight real-time accurate global pose estimates, even in LED-shortage situations. We further complete it with a 2-point global pose initialization method that loosely couples the two sensor measurements. We can hence bootstrap our system with two or more LED features observed in one camera frame. The proposed system and method are verified by extensive field experiments using dozens of self-made LED prototypes.

Smartphone-Based Cooperative Indoor Localization with RFID Technology.

In GPS-denied indoor environments, localization and tracking of people can be achieved with a mobile device such as a smartphone by processing the received signal strength (RSS) of RF signals emitted from known location beacons (anchor nodes), combined with Pedestrian Dead Reckoning (PDR) estimates of the user motion. An enhacement of this localization technique is feasible if the users themselves carry additional RF emitters (mobile nodes), and the cooperative position estimates of a group of persons incorporate the RSS measurements exchanged between users. We propose a centralized cooperative particle filter (PF) formulation over the joint state of all users that permits to process RSS measurements from both anchor and mobile emitters, as well as PDR motion estimates and map information (if available) to increase the overall positioning accuracy, particularly in regions with low density of anchor nodes. Smartphones are used as a convenient mobile platform for sensor measurements acquisition, low-level processing, and data transmission to a central unit, where cooperative localization processing takes place. The cooperative method is experimentally demonstrated with four users moving in an area of 1600 , with 7 anchor nodes comprised of active RFID (radio frequency identification) tags, and additional mobile tags carried by each user. Due to the limited coverage provided by the anchor beacons, RSS-based individual localization is inaccurate (6.1 m median error), but this improves to 4.9 m median error with the cooperative PF. Further gains are produced if the PDR information is added to the filter: median error of 3.1 m (individual) and 2.6 m (cooperative); and if map information is also considered, the results are 1.8 m (individual) and 1.6 m (cooperative). Thus, for each version of the particle filter, cooperative localization outperforms individual localization in terms of positioning accuracy.

Vision-Based Heading and Lateral Deviation Estimation for Indoor Navigation of a Quadrotor

ABSTRACT In this paper, an effective vanishing point detection method based on grid-based approach for navigation of micro aerial vehicles (MAVs) in indoor corridor environment is described. The automation and navigation of MAVs in GPS-denied indoor environments is still a challenging task. To navigate in indoor corridors, on-board camera sensor is used as a sole sensor for estimating both the vehicle position and heading. Finally, the lateral deviation and heading of an MAV from the centre towards the right or left of the corridor are computed using vanishing point coordinates between two successive frames. By exploiting geometrical constraints inside buildings, long-term stable heading information is extracted. It is shown that the proposed method effectively eliminates heading drift in indoor corridor environment and is real-time capable. The measured parameters can be used to control an MAV when it deviates from the desired path of navigation.

Autonomous Flight Control of a Nano Quadrotor Helicopter in a GPS-Denied Environment Using On-Board Vision

In this paper, a nano quadrotor helicopter which weighs about only 45 grams and has a diameter less than 0.15 m is employed for the autonomous flight control development in GPS-denied environments. Due to the very limited payload ability of the helicopter, a micro onboard vision system is designed to provide visual pose measurement. Then the attitude data obtained from a low cost micro inertial measurement unit (IMU) are fused with the visual measurement to provide accurate estimation of the helicopter's translational position and velocity. Nonlinear flight controller is designed to hold the quadrotor in a certain position and altitude without external ground motion capture system. Moreover, trajectory tracking ability is achieved with the help of a modified visual simultaneous localization and mapping (SLAM) algorithm. Experimental results are included to demonstrate the good hovering and tracking control performance of the proposed design in GPS-denied indoor and outdoor environments. To our best knowledge, few of previous works have demonstrated autonomous control ability of a quadrotor helicopter weighs less than 50 grams without the help of external ground motion capture system in GPS-denied indoor and outdoor environments.

Invariant Observer-Based State Estimation for Micro-Aerial Vehicles in GPS-Denied Indoor Environments Using an RGB-D Camera and MEMS Inertial Sensors

This paper presents a non-linear state observer-based integrated navigation scheme for estimating the attitude, position and velocity of micro aerial vehicles (MAV) operating in GPS-denied indoor environments, using the measurements from low-cost MEMS (micro electro-mechanical systems) inertial sensors and an RGB-D camera. A robust RGB-D visual odometry (VO) approach was developed to estimate the MAV’s relative motion by extracting and matching features captured by the RGB-D camera from the environment. The state observer of the RGB-D visual-aided inertial navigation was then designed based on the invariant observer theory for systems possessing symmetries. The motion estimates from the RGB-D VO were fused with inertial and magnetic measurements from the onboard MEMS sensors via the state observer, providing the MAV with accurate estimates of its full six degree-of-freedom states. Implementations on a quadrotor MAV and indoor flight test results demonstrate that the resulting state observer is effective in estimating the MAV’s states without relying on external navigation aids such as GPS. The properties of computational efficiency and simplicity in gain tuning make the proposed invariant observer-based navigation scheme appealing for actual MAV applications in indoor environments.

Visual Odometry and 3D Mapping in Indoor Environments

This paper presents a robust state estimation and 3D environment modeling approach that enables Micro Aerial Vehicle (MAV) operating in challenging GPS-denied indoor environments. A fast, accurate and robust approach to visual odometry is developed based on Microsoft Kinect. Discriminative features are extracted from RGB images and matched across consecutive frames. A robust least-square estimator is applied to get relative motion estimation. All computation is performed in real-time, which provides high frequency of 6 degree-of-freedom state estimation. A detailed 3D map of an indoor environment is also constructed.

A Kinect-based natural interface for quadrotor control

This paper presents a new and challenging approach to the control of mobile platforms. Natural user interfaces (NUIs) and visual computing techniques are used to control the navigation of a quadrotor in GPS-denied indoor environments. A visual odometry algorithm allows the platform to autonomously navigate the environment, whereas the user can control complex manoeuvres by gestures and body postures. This approach makes the human–computer interaction (HCI) more intuitive, usable, and receptive to the user’s needs: in other words, more user-friendly and, why not, fun. The NUI presented in this paper is based on the Microsoft Kinect and users can customize the association among gestures/postures and platform commands, thus choosing the more intuitive and effective interface.