Institute of Fundamental Technological Research

Search-and-rescue operations have recently been confronted with the introduction of robotic tools that assist the human search-and-rescue workers in their dangerous but life-saving job of searching for human survivors after major catastrophes. However, the world of search and rescue is highly reliant on strict procedures for the transfer of messages, alarms, data, and command and control over the deployed assets. The introduction of robotic tools into this world causes an important structural change in this procedural toolchain. Moreover, the introduction of search-and-rescue robots acting as data gatherers could potentially lead to an information overload toward the human search-and-rescue workers, if the data acquired by these robotic tools are not managed in an intelligent way. With that in mind, we present in this paper an integrated data combination and data management architecture that is able to accommodate real-time data gathered by a fleet of robotic vehicles on a crisis site, and we present and publish these data in a way that is easy to understand by end-users. In the scope of this paper, a fleet of unmanned ground and aerial search-and-rescue vehicles is considered, developed within the scope of the European ICARUS project. As a first step toward the integrated data-management methodology, the different robotic systems require an interoperable framework in order to pass data from one to another and toward the unified command and control station. As a second step, a data fusion methodology will be presented, combining the data acquired by the different heterogenic robotic systems. The computation needed for this process is done in a novel mobile data center and then (as a third step) published in a software as a service (SaaS) model. The SaaS model helps in providing access to robotic data over ubiquitous Ethernet connections. As a final step, we show how the presented data-management architecture allows for reusing recorded exercises with real robots and rescue teams for training purposes and teaching search-and-rescue personnel how to handle the different robotic tools. The system was validated in two experiments. First, in the controlled environment of a military testing base, a fleet of unmanned ground and aerial vehicles was deployed in an earthquake-response scenario. The data gathered by the different interoperable robotic systems were combined by a novel mobile data center and presented to the end-user public. Second, an unmanned aerial system was deployed on an actual mission with an international relief team to help with the relief operations after major flooding in Bosnia in the spring of 2014. Due to the nature of the event (floods), no ground vehicles were deployed here, but all data acquired by the aerial system (mainly three-dimensional maps) were stored in the ICARUS data center, where they were securely published for authorized personnel all over the world. This mission (which is, to our knowledge, the first recorded deployment of an unmanned aerial system by an official governmental international search-and-rescue team in another country) proved also the concept of the procedural integration of the ICARUS data management system into the existing procedural toolchain of the search and rescue workers, and this in an international context (deployment from Belgium to Bosnia). The feedback received from the search-and-rescue personnel on both validation exercises was highly positive, proving that the ICARUS data management system can efficiently increase the situational awareness of the search-and-rescue personnel.

This paper concerns the an intelligent mobile application for spatial design support and security domain. Mobility has two aspects in our research: The first one is the usage of mobile robots for 3D mapping of urban areas and for performing some specific tasks. The second mobility aspect is related with a novel Software as a Service system that allows access to robotic functionalities and data over the Ethernet, thus we demonstrate the use of the novel NVIDIA GRID technology allowing to virtualize the graphic processing unit. We introduce Complex Shape Histogram, a core component of our artificial intelligence engine, used for classifying 3D point clouds with a Support Vector Machine. We use Complex Shape Histograms also for loop closing detection in the simultaneous localization and mapping algorithm. Our intelligent mobile system is built on top of the Qualitative Spatio-Temporal Representation and Reasoning framework. This framework defines an ontology and a semantic model, which are used for building the intelligent mobile user interfaces. We show experiments demonstrating advantages of our approach. In addition, we test our prototypes in the field after the end-user case studies demonstrating a relevant contribution for future intelligent mobile systems that merge mobile robots with novel data centers.

Intelligent mobile system, 3D object recognition, Qualitative representation and reasoning, 3D mapping

In this paper a quantitative and qualitative evaluation of proposed ICP-based data registration algorithm, improved by parallel programming in CUDA (compute unified device architecture), is shown. The algorithm was tested on data collected with a 3D terrestrial laser scanner Z + F Imager 5010 mounted on the mobile platform PIONNER 3AT. Parallel implementation enables data registration on-line, even using a laptop with a standard hardware configuration (graphic card NVIDIA GeForce 6XX/7XX series). Robustness is assured by the use of CUDA-enhanced fast NNS (nearest neighbor search) applied for ICP (iterative closest point) with SVD (singular value decomposition) solver. The evaluation is based on the reference ground truth data registered with geodetic precision. The geodetic approach extends our previous work and gives an accurate benchmark for the algorithm. The data were collected in an urban area under a demolition scenario in a real environment. We compared four registration strategies concerning data preprocessing, such as subsampling and vegetation removal. The result is the analysis of measured performance and the accuracy of the geometric maps. The system provides accurate metric maps on-line and can be used in several applications such as mobile robotics for construction area modelling or spatial design support. It is a core component for our future work on mobile mapping systems.

Iterative closest point, Data registration, Mobile mapping, CUDA parallel programming, Spatial design support

W artykule przedstawiono projekt autonomicznego robota inspekcyjnego. Ze względu na fakt, że komercyjne rozwiązania nie oferują satysfakcjonującej funkcjonalności w stosunkowo niskiej cenie zdecydowano się zaprojektować autonomicznego robota inspekcyjnego na bazie komercyjnej platformy wyposażonej w autorskie rozwiązanie laserowego systemu pomiarowego 3D. Projekt lasera 3D wykonano z wykorzystaniem technik szybkiego prototypowania metodą druku 3D. Autonomiczny robot mobilny nawigowany jest na podstawie systemu IMU (Inertial Measurement Unit) ze zintegrowanym GPS (Global Positioning System). Opracowane rozwiązanie dostarcza użytkownikowi danych w postaci map lokalnych 3D wraz z częściową analizą semantyczną (obliczanie wektorów normalnych dla chmury punktów metodą PCA Principal Component Analysis) w trybie on-line. Przeprowadzono eksperymenty weryfikujące poprawność działania systemu. W rezultacie powstało nowoczesne stanowisko badawcze, które może być wykorzystane do kolejnych badań z wykorzystaniem mobilnych systemów inspekcyjnych.

robot inspekcyjny, laserowy system pomiarowy 3D, PCA (Principal Component Analysis)

This paper deals with research related with the improvements of state of the art algorithms used in robotic applications based on parallel computation. The main goal is to decrease the computational complexity of 3D cloud of points processing in applications as: data filtering, normal vector estimation, data registration, and point feature histogram calculation. The presented results improve the efficiency of existing implementations with minimal lost of accuracy. The main contribution is a regular grid decomposition originally implemented for nearest neighborhood search. This data structure is the basis for all presented methods, it provides an efficient method for decreasing the time of computation. The results are compared with well-known robotic frameworks such as PCL and 3DTK.

W artykule przedstawiono mobilny system tworzenia przestrzennej dokumentacji semantycznej. Zaproponowano nową metodę filtracji oraz rejestracji danych wykorzystującą obliczenia równoległe (NVIDIA FERMI). Opracowany system informatyczny umożliwia gromadzenie danych przestrzennych z wykorzystaniem geodezyjnego systemu pomiarowego 3D oraz pozwala na etykietowanie obiektów. Tworzona mapa semantyczna jest dostępna z poziomu dowolnego urządzenia mobilnego (laptop, smartphone, tablet).

mapa semantyczna, przestrzenna dokumentacja semantyczna, skanowanie laserowe, chmura punktów, obliczenia równoległe, wizualizacja

This paper shows the results of a semi autonomous mobile robot tested in inspection missions during ENRICH 2023 and ELROB 2024. After successful ENRICH 2023 we decided to improve our system by adding LiDAR (Light Detection and Ranging) motion compensation with IMU (Inertial Measurement Unit). Our goal is to provide an affordable robotic solution as open source project available at https://github.com/JanuszBedkowski/msas_enrich_2023. Everything was fine till realistic test during ELROB 2024. Our system works well in 2D scenarios. It is not robust against large slopes. In this paper we show system overview and elaborate its limitations. We demonstrated the use of our open source project https://github.com/MapsHD/HDMapping for 3D map building with the mobile mapping system attached to the robot.

mobile robot, semi autonomous, real world task, LiDAR

In this paper the GPU-accelerated range sensors simulation is discussed. Range sensors generate large amount of data per second and to simulate these high-performance simulation is needed. We propose to use parallel ray tracing on graphics processing units to improve the performance of range sensors simulation. The multiple range sensors are described and simulated using NVIDIA OptiX ray tracing engine. This work is focused on the performance of the GPU acceleration of range images simulation in complex environments. Proposed method is tested using several state-of-the-art ray tracing datasets. The software is publicly available as an open-source project SensorSimRT.

Ray tracing, RGB-D sensors, Simulation

We propose an open source robotic 3D mapping framework based on Robot Operating System, Point Cloud Library and Cloud Compare software extended by functionality of importing and exporting datasets. The added value is an integrated solution for robotic 3D mapping and new publicly available datasets (accurate 3D maps with geodetic precision) for evaluation purpose Datasets were gathered by mobile robot in stop scan fashion. Presented results are a variety of tools for working with such datasets, for task such as: preprocessing (filtering, down sampling), data registration (ICP, NDT), graph optimization (ELCH, LUM), tools for validation (comparison of 3D maps and trajectories), performance evaluation (plots of various outputs of algorithms). The tools form a complete pipeline for 3D data processing. We use this framework as a reference methodology in recent work on SLAM algorithms.

Three-dimensional displays, Robot kinematics, Cameras, Mobile communication, Robot sensing systems, XML

This paper concentrates on the topic of gathering, processing and presenting 3D data for use in Search and Rescue operations. The data are gathered by unmanned ground platforms, in form of 3D point clouds. The clouds are matched and transformed into a consistent, highly accurate 3D model. The paper describes the pipeline for such matching based on Iterative Closest Point algorithm supported by loop closing done with LUM method. The pipeline was implemented for parallel computation with Nvidia CUDA, which leads to higher matching accuracy and lower computation time. An analysis of performance for multiple GPUs is presented. The second problem discussed in the paper is immersive visualization of 3d data for search and rescue personnel. Five strategies are discussed: plain 3D point cloud, hypsometry, normal vectors, space descriptors and an approach based on light simulation through the use of NVIDIA OptiX Ray Tracing Engine. The results from each strategy were shown to end users for validation. The paper discusses the feedback given. The results of the research are used in the development of a support module for ICARUS project.

Three-dimensional displays, Data visualization, Graphics processing units, Image color analysis, Computational modeling, Solid modeling, Pipelines

This paper shows evaluation result of the mobile robotic system for Urban Search and Rescue performed during Eurathlon 2013 robotic competition by IAIR-IMM team. Our team was competing in two scenarios: a) Reconnaissance and surveillance in urban structures (USAR), b) Search and rescue in a smoke-filled underground structure. The main task for this system from our team point of view was to build 3D metric map of the environment and to find OPIs (Objects of Potential Interest). Therefore in this paper we described the vision system for objects recognition and 3D map building. The system is composed of mobile robot equipped with camera, 3D laser measurement system and base station composed of computer equipped with NVIDIA GPU for parallel processing of derived clouds of points. The main focus of the work was to improve the performance of the operator controlling the robot in harsh environment. We achieved satisfactory results that could be still improved in many aspects. In experimental part we demonstrated validation of vision recognition system and 3D maps built during preparation trials and during final competition. The best quantitative result of this work was 3rd place in USAR scenario. Unfortunately, we could not build the map in a smoke-filled underground structure, but the result is also very interesting for future developments.

Eurathlon, mobile robot

Search and rescue (SAR) teams often face several complex and dangeroustasks, witch could be aided by unmanned robotic vehicles (UV). UV agents can potentially be used to decrease the risk in the loss of lives both of the rescuers and victims and aid in the search and transportation and survivors and in the removal of debris in a catastrophe scenario. Depending on the nature of a catastrophe and its geographical location, there are potentially three types of UV contemplates, their operators need prior training and certification. To train and certify the operators a tool (serious game) is under development. In this paper we will make an overview about our approach in its development. This game uses a typical client-server architecture where all client agents (virtual UVs and operator client interfaces) share the same immersive virtual environment which is generated through the merging of GIS data and a semantic model extracted from 3D lase data. There will be several types of scenarios suitable to several types of catastrophe situations.Each of these scenarios has its own mission plan for the trainees to follow. The game will also provide an interface for mission planning so that each mission plan will be carefully designed to accurately correspond to a matrix of skills. This matrix lists a set of common skills in various different UV operational case studies which will allow the certification of operators.

Affordable technological solutions are always welcome, thus we decided to test the backpack based 3D mapping system for digitizing USAR scenes. The system is composed of Intel RealSense Tracking Camera T265, three Velodynes VLP16, custom electronics for multi-lidar synchronization and VR Zotac GO backpack computer equipped with GeForce GTX1070. This configuration allows the operator to collect and process 3D point clouds to obtain a consistent 3D map. To reach satisfactory accuracy we use RealSense as initial guess of trajectory from Visual Odometry (VO). Lidar odometry corrects trajectory and reduces scale error from VO. The academic 6DSLAM is used for loop closure and finally classical ICP algorithm refines the final 3D point cloud. All steps can be done in the field in reasonable time. The VR backpack can be used for virtual travel over digital content afterwords. Additionally deep neural network is used to perform online object detection using Relsense camera input.