Extracting 3D Indoor Maps with Any Shape Accurately Using Building Information Modeling Data

Indoor maps lay the foundation for most indoor location-based services (LBS). Building Information Modeling (BIM) data contains multiple dimensional computer-aided design information. Some studies have utilized BIM data to automatically extract 3D indoor maps. A complete 3D indoor map consists of both floor-level maps and cross-floor paths. Currently, the floor-level indoor maps are mainly either grid-based maps or topological maps, and the cross-floor path generation schemes are not adaptive to building elements with irregular 3D shapes. To address these issues, this study proposes a novel scheme to extract an accurate 3D indoor map with any shape using BIM data. Firstly, this study extracts grid-based maps from BIM data and generates the topological maps directly through the grid-based maps using image thinning. A novel hybrid indoor map, termed Grid-Topological map, is then formed by the grid-based maps and topological maps jointly. Secondly, this study obtains the cross-floor paths from cross-floor building elements by a four-step process, namely X-Z projection, boundary extraction, X-Z topological path generation, and path-BIM intersection. Finally, experiments on eight typical types of cross-floor building elements and three multi-floor real-world buildings were conducted to prove the effectiveness of the proposed scheme, the average accuracy rates of the evaluated paths are higher than 88%. This study will advance the 3D indoor maps generation and inspire the application of indoor maps in indoor LBS, indoor robots, and 3D geographic information systems.

A Review on Map-Merging Methods for Typical Map Types in Multiple-Ground-Robot SLAM Solutions

When multiple robots are involved in the process of simultaneous localization and mapping (SLAM), a global map should be constructed by merging the local maps built by individual robots, so as to provide a better representation of the environment. Hence, the map-merging methods play a crucial rule in multi-robot systems and determine the performance of multi-robot SLAM. This paper looks into the key problem of map merging for multiple-ground-robot SLAM and reviews the typical map-merging methods for several important types of maps in SLAM applications: occupancy grid maps, feature-based maps, and topological maps. These map-merging approaches are classified based on their working mechanism or the type of features they deal with. The concepts and characteristics of these map-merging methods are elaborated in this review. The contents summarized in this paper provide insights and guidance for future multiple-ground-robot SLAM solutions.

Traffic Intersection Re-Identification Using Monocular Camera Sensors

Perception of road structures especially the traffic intersections by visual sensors is an essential task for automated driving. However, compared with intersection detection or visual place recognition, intersection re-identification (intersection re-ID) strongly affects driving behavior decisions with given routes, yet has long been neglected by researchers. This paper strives to explore intersection re-ID by a monocular camera sensor. We propose a Hybrid Double-Level re-identification approach which exploits two branches of Deep Convolutional Neural Network to accomplish multi-task including classification of intersection and its fine attributes, and global localization in topological maps. Furthermore, we propose a mixed loss training for the network to learn the similarity of two intersection images. As no public datasets are available for the intersection re-ID task, based on the work of RobotCar, we propose a new dataset with carefully-labeled intersection attributes, which is called “RobotCar Intersection” and covers more than 30,000 images of eight intersections in different seasons and day time. Additionally, we provide another dataset, called “Campus Intersection” consisting of panoramic images of eight intersections in a university campus to verify our updating strategy of topology map. Experimental results demonstrate that our proposed approach can achieve promising results in re-ID of both coarse road intersections and its global pose, and is well suited for updating and completion of topological maps.

Research on optimal takeoff positions of UAV integrated GNSS - RTK in producing large scale topological maps for open - pit mines

Unmanned aerial vehicles (UAV) are widely used for establishing large scale topological maps. Recently, drones have been integrated with high-quality GNSS receivers which allows real time kinematic positioning (RTK), so are called UAV/RTK. This technology is beneficial to surveyors as they do not need to establish many ground control points in mapping such a complex terrain as open-pit mines. DJI Phantom 4 RTK (P4K) is a UAV/RTK which is of much interest due to its small size and low cost. For open-pit mines, the takeoff position of P4K needs to be seriously considered because of its influence on the accuracy of the digital surface model (DSM) and safety of survey flights. This article presents the method of determining the optimal takeoff positions for UAV in large scale mapping for open pit mines. To evaluate this method, a site of steep and rugged terrain with an area of 80 hectares at the Coc Sau coal mine was chosen as the study area. The results indicate that two optimal locations with altitudes of +50 m and +160 m could be used for taking off the P4K. The accuracy of DSM generated from UAV images using the optimal positions satisfied the accuracy requirement of large scale topological maps at the deepest area of the mine (the altitude of -60 m).

Occupancy Grid and Topological Maps Extraction from Satellite Images for Path Planning in Agricultural Robots

Robotics will significantly impact large sectors of the economy with relatively low productivity, such as Agri-Food production. Deploying agricultural robots on the farm is still a challenging task. When it comes to localising the robot, there is a need for a preliminary map, which is obtained from a first robot visit to the farm. Mapping is a semi-autonomous task that requires a human operator to drive the robot throughout the environment using a control pad. Visual and geometric features are used by Simultaneous Localisation and Mapping (SLAM) Algorithms to model and recognise places, and track the robot’s motion. In agricultural fields, this represents a time-consuming operation. This work proposes a novel solution—called AgRoBPP-bridge—to autonomously extract Occupancy Grid and Topological maps from satellites images. These preliminary maps are used by the robot in its first visit, reducing the need of human intervention and making the path planning algorithms more efficient. AgRoBPP-bridge consists of two stages: vineyards row detection and topological map extraction. For vineyards row detection, we explored two approaches, one that is based on conventional machine learning technique, by considering Support Vector Machine with Local Binary Pattern-based features, and another one found in deep learning techniques (ResNET and DenseNET). From the vineyards row detection, we extracted an occupation grid map and, by considering advanced image processing techniques and Voronoi diagrams concept, we obtained a topological map. Our results demonstrated an overall accuracy higher than 85% for detecting vineyards and free paths for robot navigation. The Support Vector Machine (SVM)-based approach demonstrated the best performance in terms of precision and computational resources consumption. AgRoBPP-bridge shows to be a relevant contribution to simplify the deployment of robots in agriculture.

Asymptotic laws for knot diagrams

International audience We study random knotting by considering knot and link diagrams as decorated, (rooted) topological maps on spheres and sampling them with the counting measure on from sets of a fixed number of vertices n. We prove that random rooted knot diagrams are highly composite and hence almost surely knotted (this is the analogue of the Frisch-Wasserman-Delbruck conjecture) and extend this to unrooted knot diagrams by showing that almost all knot diagrams are asymmetric. The model is similar to one of Dunfield, et al.