Search

This work majorly focused on development of rescue robot systems for children falling into bore well environment. The countries like India there have been several accidents and dead are happening particularly children below 3 years due to bore well environment which is left uncovered. The lifesaving team even army members spend hours to days but 70% of the attempts are unsuccessful to save these little kids because of complicated process. Our robot system mainly involves following process; Approaching the children, Supervision the children, Taking children out. And also our work focused on Safe Handling of the children. Therefore our work deals with concepts of rescue robot systems in bore well environment with semi-automated mechanisms.

In recent years, several robots have been developed and deployed to perform casualty extraction tasks. However, the majority of these robots are overly complex, and require teleoperation via either a skilled operator or a specialised device, and often the operator must be present at the scene to navigate safely around the casualty. Instead, improving the autonomy of such robots can reduce the reliance on expert operators and potentially unstable communication systems, while still extracting the casualty in a safe manner. There are several stages in the casualty extraction procedure, from navigating to the location of the emergency, safely approaching and loading the casualty, to finally navigating back to the medical assistance location. In this paper, we propose a Hierarchical Decomposed-Objective based Model Predictive Control (HiDO-MPC) method for safely approaching and manoeuvring around the casualty. We implement this controller on ResQbot — a proof-of-concept mobile rescue robot we previously developed — capable of safely rescuing an injured person lying on the ground, i.e. performing the casualty extraction procedure. HiDO-MPC achieves the desired casualty extraction behaviour by decomposing the main objective into multiple sub-objectives with a hierarchical structure. At every time step, the controller evaluates this hierarchical decomposed objective and generates the optimal control decision. We have conducted a number of experiments both in simulation and using the real robot to evaluate the proposed method’s performance, and compare it with baseline approaches. The results demonstrate that the proposed control strategy gives significantly better results than baseline approaches in terms of accuracy, robustness, and execution time, when applied to casualty extraction scenarios.

A number of rescue robots for quick information gathering and safe rescue operations at the time of earthquake have been developed. Many robots adopt the crawler type. It is suitable for irregular terrain such as rubble and wasteland of the disaster site. In this paper, we focus on the traversing performance of robot functions required, and aim to be able to overcome the higher level difference by seeking the performance to overcome the step. We produce a robot equipped with sub crawlers and report the results of experiments.

Rescue robots are expected to carry out reconnaissance and dexterity operations in unknown environments comprising unstructured obstacles. Although a wide variety of designs and implementations have been presented within the field of rescue robotics, embedding all mobility, dexterity, and reconnaissance capabilities in a single robot remains a challenging problem. This paper explains the design and implementation of Karo, a mobile robot that exhibits a high degree of mobility at the side of maintaining required dexterity and exploration capabilities for urban search and rescue (USAR) missions. We first elicit the system requirements of a standard rescue robot from the frameworks of Rescue Robot League (RRL) of RoboCup and then, propose the conceptual design of Karo by drafting a locomotion and manipulation system. Considering that, this work presents comprehensive design processes along with detail mechanical design of the robot’s platform and its 7-DOF manipulator. Further, we present the design and implementation of the command and control system by discussing the robot’s power system, sensors, and hardware systems. In conjunction with this, we elucidate the way that Karo’s software system and human–robot interface are implemented and employed. Furthermore, we undertake extensive evaluations of Karo’s field performance to investigate whether the principal objective of this work has been satisfied. We demonstrate that Karo has effectively accomplished assigned standardized rescue operations by evaluating all aspects of its capabilities in both RRL’s test suites and training suites of a fire department. Finally, the comprehensiveness of Karo’s capabilities has been verified by drawing quantitative comparisons between Karo’s performance and other leading robots participating in RRL.

According to the statistics on numbers and rates of fire disaster in world, millions of lives of peoples, animals and on- duty fire fighter are lost every year. It gives the high demand for an autonomous machine to operate the fire disaster rescue operation efficiently and help to fire fighter team. The proposed paper involves the design of a robot that can analysis the situation at victim place and send the full report to the server of fire fighter team which can help them to deal with the disaster situation. Robot also aids the fire fighter team to search the victim and rescue them to safe places. The robot will not only be localize itself but also aids to turn off the fire. The Robot will help to rescue peoples and animals in fire disaster in efficient manner with least harm to rescue team.

Search and rescue has become a key technology to be solved, but it is difficult for most rescue robots to implement safe and effective rescue for survivors. Based on two degree of freedom five bar variant scissor mechanism, this paper proposes a design scheme of combined bionic multi-arm cooperative rescue robot actuator. The actuator was designed to imitate elephant trunk, octopus and armadillo and the working track of rescue manipulator is designed by the cross section of human body. The kinematics of the actuator is analyzed based on the vector method, and the positive position solution and Jacobian matrix are obtained. The optimal design parameters of the actuator are determined, and the experimental prototype of the rescue robot actuator is developed, which lays the foundation for the development of the new rescue robot.

Diese Arbeit beschäftigt sich mit der Dokumentation der Konzeptionierung und Konstruktion eines Roboters. Inhaltlicher Kern ist dabei die Entwicklung des Teilbereichs „Arm“. Hintergrund der Arbeit ist ein im Rahmen des Bachelor Studiengangs „High Tech Manufacturing“ der FH Campus Wien durchgeführtes Konstruktionsprojekt. Aufgabe dieses Konstruktionsprojektes ist es bereits bestehende Konzepte zu analysieren und diese zu verbessern oder anhand dieser ein neues verbessertes Konzept zu entwickeln. Die Entwicklung umfasst dabei rein die Auslegung der Hardware, welche die Konstruktion und Auslegung sämtlicher mechanischer Komponenten, sowie die Auslegung aller zum Bewegungsablauf notwendigen Aktoren und Sensoren umfasst. Nicht Teil der Arbeit ist die Software sowie dazugehörige Steuerelektronik. Das gesamte Konzept ist in einzelne eigenständige Arbeitspakete unterteilt, die jeweils von einzelnen Personen bearbeitet werden. Trotz der strikten Trennung der einzelnen Teilbereiche, interagieren diese jedoch, an definierten Schnittstellen, im Sinne des Gesamtprojektes. Die Entstehung des Gesamtkonzeptes sowie Referenzen zu weiteren Teilbereichen sind daher essenzieller Bestandteil dieser Arbeit. Das Konstruktionsprojekt dient zur Entwicklung und Realisierung eines Rescue Robots zur Teilnahme einer Mannschaft an der RoboCup Rescue League. Dabei handelt es sich um einen Wettbewerb, in dem eigens entwickelte Roboter in Such- und Rettungsszenarien antreten. Aus diesem Grund gelten das Reglement des Wettbewerbs, sowie möglichst kostengünstige Fertigung als wichtigste Rahmenbedingungen für das Projekt. Die Konstruktion des Arms wird als CAD Modell durchgeführt und mit Hilfe der Simulationsmöglichkeiten der Konstruktionssoftware und mathematischen Berechnungen ausgelegt. Als Ergebnis steht daher ein vollständig ausgearbeitetes Modell des Armes bei dem alle Komponenten auf ihre Belastungen im realen Einsatz werden. Die aus dem CAD-Modell erstellten Fertigungszeichnungen, sowie die ausgewählten Zukaufteile können somit direkt für die Realisierung des Prototypen übernommen werden. This thesis deals with the documentation of the conceptual design and construction of a robot. The core content is the development of the subarea "arm". The background of the work is a design project carried out as part of the bachelor's degree program "High Tech Manufacturing" at the FH Campus Wien. The task of this design project is to analyse already existing concepts, to improve them, or to develop a new improved concept based on them. The development includes only the design of the hardware, which includes the construction and design of all mechanical components, as well as the design of all actuators and sensors necessary for the motion sequence. Not part of the work is the software and associated control electronics. The entire concept is divided into individual independent work packages, each of which is handled by a separate person. Despite the strict separation of the individual sub-areas, these interact, however, at defined interfaces, in the sense of the overall project. The development of the overall concept as well as references to other sub-areas are therefore an essential part of this work. The construction project serves for the development and realization of a Rescue Robot for the participation of a team in the RoboCup Rescue League. This is a competition in which specially developed robots compete in search and rescue scenarios. For this reason, the regulations of the competition, as well as the most cost-effective production possible, are considered the most important framework conditions for the project. The construction of the arm is carried out as a CAD model and is designed with the help of the simulation possibilities of the construction software and mathematical calculations. The result is a fully developed model of the arm in which all components are simulated and calculated for their loads in real use. The production drawings created from the CAD model, as well as the selected purchased parts, can thus be used directly for the realization of the prototype.

In real-world applications such as rescue robots, service robots, mobile mining robots, and mine searching robots, an autonomous mobile robot needs to reach multiple targets with the shortest path. This paper proposes an Immune System algorithm (ISA) for real-time map building and path planning for multi-target applications. Once a global route is planned by the ISA, a foraging-enabled trail is created to guide the robot to the multiple targets. A histogram-based local navigation algorithm is used to navigate the robot along a collision-free global route. The proposed ISA models aim to generate a path while a mobile robot explores through terrain with map building in unknown environments. In this paper, we explore the ISA algorithm with simulation studies to demonstrate the capability of the proposed ISA in achieving a global route with minimized overall distance. Simulation studies demonstrate that the real-time concurrent mapping and multi-target navigation of an autonomous robot is successfully performed under unknown environments.

This paper proposes a path tracking control algorithm of tracked mobile robots based on Preview Linear Model Predictive Control (MPC), which is used to achieve autonomous driving in the unstructured environment under an emergency rescue scenario. It is the future trend to realize the communication and control of rescue equipment with 6G and edge cloud cooperation. In this framework, linear MPC (LMPC) is suitable for the path tracking control of rescue robots due to its advantages of less computing resources and good real-time performance. However, in such a scene, the driving environment is complex and the path curvature changes greatly. Since LMPC can only introduce linearized feedforward information, the tracking accuracy of the path with large curvature changes is low. To overcome this issue, combined with the idea of preview control, preview-linear MPC is designed in this paper. The controller is verified by MATLAB/Simulink simulation and prototype experiment. The results show that the proposed method can improve the tracking accuracy while ensuring real-time performance and has better tracking performance for the path with large curvature variation.

In this era of a politically competitive world, there is a growing demand for the use of military robots to aid soldiers to perform perilous missions. This project focuses on the design and build of a semi-autonomous, solar-powered, unmanned robotic system operating with real-time object detection function, used for various military and rescue operations such as explosives disposal, enemy territory surveillance, and search and rescue. The military robotic system is instilled with a robotic arm for explosives disposal, a sensory circuit for analysis of the environmental composition of the area under surveillance, and a Raspberry PI for real-time object detection. The commands for the motion of the robotic arm and the robotic body are given using a Graphical User Interphase (GUI). The effectiveness in performing perilous missions can be accomplished by the utilization of Artificial Intelligence (AI). Real-time object detection with deep learning techniques is utilized in this robotic system to identify objects within the frame of the camera and tag the objects with the accuracy rate of computations. Data transmission and receiving is through Zigbee and Wi-Fi communication technologies. The proposed robotic system overcomes the weakness in the existing models and thus provides better support in military operations.

Diese Arbeit beschäftigt sich mit der Erstellung eines Gehäusekonzepts für einen Rescue Robot. Die Besonderheit am Konzept ist die schnelle Zerlegbarkeit des Gehäuses. Die Arbeit soll die Vor- und Nachteile einer solchen Konstruktion zeigen. Die Eigenschaft des schnellen Zerlegens wird durch zwei übereinander schiebbare Gehäusehälften erzeugt. Die seitlichen Gehäuseplatten sollen der Konstruktion die nötige Stabilität liefern. In der Arbeit beschäftigt man sich mit den Methoden der Fertigung der einzelnen Gehäuseteile. Außerdem wird sich mit der Frage des richtigen Werkstoffes für diese Konstruktion gewidmet. Ein Test der Gehäusestabilität in Form einer Simulation wird am Ende der Arbeit durchgeführt. Mithilfe dieser Simulation wurde das Gehäuse auf seine Formstabilität geprüft. Die Gewichtsverteilung in Verbindung mit der optimalen Anordnung der Zusatzkomponenten wird im Mittelteil der Arbeit behandelt. In diesem Teil war es notwendig die Spannungsversorgung im Gehäuse unterzubringen. Es wurde besonders auf eine günstige Positionierung dieser geachtet, da dieses Bauteil die Gewichtsverteilung stark beeinflusst. Im letzten Kapitel wird die Arbeit mit den anderen am Projekt beteiligten Arbeiten zusammengefügt. This work deals with the creation of a housing concept for a rescue robot. The special feature of the concept is the quick disassembly of the housing. The work should show the advantages and disadvantages of such a construction. The property of quick disassembly is created by two housing halves that can be pushed over one another. The side housing plates should provide the construction with the necessary stability. The thesis also deals with the methods of manufacturing the individual housing parts. In addition, the question of the right material for this construction is devoted. A housing stability test in the form of a simulation is carried out at the end of the work. With the help of this simulation, the shape of the housing was checked. The weight distribution in connection with the optimal arrangement of the additional components is dealt with in the middle part of the work. In this part it was necessary to place the power supply in the housing. Special attention was paid to the favorable positioning of these, since this component strongly influences the weight distribution. In the last chapter, the work is combined with the other work involved in the project.

Perception is a boon which is one of its kinds for every human being around the world. In this modern world, where technology has been tremendously developing, there has also been an escalation in the number of people being born with vision impairment. This paper provides a solution with a system that serves as an ability to hear and see for the assistive technologies such as service robots and rescue robots which could help for the old and crippled. This research deals with the integration of an object recognition technique with speech recognition using the robot operating system (ROS) to come up with a speech-based visual perceiving system that can aid the visually impaired people. The proposed object recognition uses Kinect v2 camera and YOLO algorithm for efficient object recognition. Here, mutual communication between the visually challenged and robot is established. This paper also discusses the system architecture implemented and tested in real and noisy environments.

Die vorliegende Arbeit beschäftigt sich mit der Konzeptionierung und Auslegung eines Kettenfahrwerks und der dazugehörigen Antriebstechnik. Der geplante Einsatzzweck ist die Verwendung als Hauptantrieb eines Bergungsroboters mit dem Namen RCR-20, welcher für das ResQ. Bots Team der FH Campus Wien in der RoboCup Rescue League antreten soll. Der RCR-20 wurde von sieben Personen entwickelt und basiert auf zwei bestehenden Konstruktionen, welche dem Team übergeben wurden. Der konstruktive Aufwand wurde dabei in einzelne Teilbereiche aufgeteilt und jedem Teammitglied ein solcher zur Bearbeitung zugeordnet. Im Rahmen dieser Arbeit wird dabei der Entwicklungsprozess des Teilbereichs Hauptantrieb vorgestellt. Der erste Teil der Arbeit dient der Orientierung. Hierbei wird zunächst die Ausgangslage beschrieben und die beiden bestehenden Konstruktionen analysiert. Es wird außerdem das Team mit den jeweiligen Teilbereichen vorgestellt und näher auf den Hauptantrieb eingegangen. Es werden außerdem die im Rahmen dieser Arbeit verwendeten Methoden erläutert. Den Abschluss bildet die sich daraus ergebende Forschungsfrage. Der zweite Teil dieser Arbeit widmet sich der Recherche und fasst das notwendige Hintergrundwissen zusammen. Hier werden zuerst alle Anforderungen, die den Hauptantrieb betreffen, ermittelt. Anschließend werden zwei erfolgreiche Bergungsroboter-Konzepte analysiert, um einen Blick für neue Ansätze zu gewinnen. Das letzte Kapitel fasst sodann die Informationen über Kettenfahrwerken zusammen und bildet damit die Grundlage für den Konstruktionsprozess. Der dritte Teil beschäftigt sich mit dem Konstruktionsprozess selbst. Die Ergebnisse der Recherche werden in geplante Veränderungen übersetzt und die Umsetzung dieser anhand der einzelnen Komponenten veranschaulicht. Im letzten Teil der Arbeit werden die Ergebnisse in Bezug auf die Forschungsfragen zusammengefasst und weitere Verbesserungspotenziale diskutiert. The present work deals with the conception and layout of a crawler chassis and its associated drive technology. Its planned application is the use as the main drive of a rescue robot with the name RCR-20, which will compete for the ResQ. Bots Team of the FH Campus Wien in the RoboCup Rescue League. The RCR-20 was developed by a team of seven people and is based on two existing design-concepts, both of which were developed by predecessors of said team. In order to create an efficient workflow, the workload was divided into seven sub-areas, each assigned to a team member. The present work details the development of the sub-area of the main drivetrain. The first part of this thesis should serve as orientation. First, the initial situation is laid out, and the two existing design-concepts are analysed. The team members with their respective sub-areas are also presented and the main drivetrain is discussed in more detail. This part concludes with a short summary of the methods used as part of the scientific process and the resulting research questions. The second part of this thesis is devoted to research and is intended to summarize the necessary background knowledge. Here, all requirements relating to the main drivetrain are determined first. Then two successful recovery robot concepts are analysed, to discover potential new approaches. The last chapter then summarizes the basics of crawler chassis, in order to base the construction process on the latest developments of technology and research. The third part deals with the construction process itself. The results of the research are translated into planned changes and the implementation of these changes is illustrated using the individual components. In the last part of the work, the results are summarized in relation to the research questions and further potential for improvement is discussed.

Rescue robots are expected to soon become commonplace at disaster sites, where they are increasingly being deployed to provide rescuers with improved access and intervention capabilities while mitigating risks. The presence of robots in operation areas, however, is likely to carry a layer of additional ethical complexity to situations that are already ethically challenging. In addition, limited guidance is available for ethically informed, practical decision-making in real-life disaster settings, and specific ethics training programs are lacking. The contribution of this paper is thus to propose a tool aimed at supporting ethics training for rescuers operating with rescue robots. To this end, we have designed an interactive text-based simulation. The simulation was developed in Python, using Tkinter, Python's de-facto standard GUI. It is designed in accordance with the Case-Based Learning approach, a widely used instructional method that has been found to work well for ethics training. The simulation revolves around a case grounded in ethical themes we identified in previous work on ethical issues in rescue robotics: fairness and discrimination, false or excessive expectations, labor replacement, safety, and trust. Here we present the design of the simulation and the results of usability testing.

Diese Bachelorarbeit beschäftigt sich mit der Optimierung und Fertigung des mechanischen Aufbaus des Bodys und Hauptantriebs eines Bergungsroboters für die Teilnahme an den Wettbewerben der RoboCup Rescue League. Grundlage der Arbeit bildet die bestehende Konstruktion eines Bergungsroboters, welche von sieben Studierenden der FH Campus Wien im Rahmen deren Bachelorarbeit 1 bereits erarbeitet wurde. Der Bergungsroboter, welcher im Zuge dieser BA 2 dabei optimierte und anschließend auch gefertigt wurde, wird dem Res.Q Bots Austria Team, welches von der FH und externen Sponsoren unterstützt wird, in weiterer Folge als mechanischer Aufbau dienen für die Umsetzung ihres ersten eigenen Bergungsroboters. Das Projektteam, welches sich für das Thema der Optimierung und Fertigung des Bergungsroboters im Rahmen der Bachelorarbeit 2 entschieden hat, besteht aus drei Teammitgliedern. Um das Projekt möglichst effizient und effektiv abzuarbeiten, wurden zu Beginn des Projektes die Teilbereiche des Bergungsroboters in Abstimmung auf die drei Projektmitglieder aufgeteilt. Diese Arbeit behandelt dabei speziell die zwei Teilbereiche des Bodys und Hauptantriebs. Anschließend wurde die bestehende Konstruktion durch die Anwendung der verschiedensten Methoden auf ihre Schwachstellen und Mängel bezüglich der Dimensionierung, Fertigbarkeit, dem Gewicht und speziell auch den Kosten für die Umsetzung untersucht. Dies war entscheidend um das Budget des Res.Q Bots Team, welches für die Umsetzung dieser Arbeit zur Verfügung stand, nicht zu überschreiten. Nachdem die Schwachstellen erfasst wurden, wurden konstruktive Lösungen entwickelt, um die beiden Teilbereiche bezüglich der genannten Punkte zu optimieren. Um die Kosten dabei gering zu halten, wurde bereits bei der Konstruktion darauf geachtet, dass sich die Komponenten, wenn möglich mit Fertigungstechnologien umsetzen lassen, welche auch an der Werkstätte des Res.Q Bots Team zur Verfügung stehen bzw. sich die Komponenten auf der FLM-Anlage des Verfassers dieser Arbeit anfertigen lassen. Auch an dieser Stelle wurden wieder die verschiedensten Methoden angewendet, um die konstruktiven Lösungen schon während der Konstruktionsphase z. B. mittels Belastungssimulationen und / oder dem Rapid Prototyping zu überprüft. Um die Komponenten nach Abschluss der Konstruktion auch in Eigen- bzw. externer Fertigung anfertigen zu können, wurden anschließend die Fertigungsunterlagen zu den zwei Teilbereichen des Bodys und Hauptantriebs erstellt. Mit den Fertigungsunterlagen wurden mehrere Angebote eingeholt und auch versucht, Sponsoren für das Projekt zu begeistern, um die Ausgaben auch hier wieder möglichst gering zu halten. Anschließend wurden die Bestellungen ausgelöst bzw. die Teile in Eigenfertigung produziert. Dabei kamen bei der Fertigung die modernsten Fertigungstechnologien zum Einsatz wie z. B. das Wasser- und Laserstrahlschneiden wie auch die additive Fertigung mittels des SLS- und FLM-Druckes. Abschließend wurden die beiden Teilbereiche sowie auch der gesamte Bergungsroboter unter Mithilfe des Res.Q Bots Teams montiert und dieser zusammen mit den CAD-Files und den Entwicklungsunterlagen an das Res.Q Bots Team übergeben. This bachelor thesis deals with the optimization and manufacturing of the mechanical structure of the body and drivetrain of a rescue robot for participation in the competitions of the RoboCup Rescue League. The basis of the work is the existing construction of a rescue robot, which was already developed by seven students of the FH Campus Wien as part of their bachelor thesis 1. The rescue robot, which was optimized in the course of this bachelor thesis 2 and then also manufactured, will subsequently serve the Res.Q Bots Austria team, which is supported by the FH and external sponsors, as a mechanical structure for the implementation of their first own rescue robot. The project team that decided on the topic of optimizing and manufacturing the rescue robot as part of bachelor thesis 2 consists of three team members. In order to work through the project as efficiently and effectively as possible, the sub-areas of the rescue robot were divided up between the three project members at the beginning of the project. This thesis deals specifically with the two sub-areas of the body and the drivetrain. The existing construction was then examined for its weak points and deficiencies in terms of dimensioning, manufacturability, weight and especially the costs of implementation using a wide variety of methods. This was crucial in order not to exceed the budget of the Res.Q Bots team, which was available for the implementation of this work. After the weak points had been identified, constructive solutions were developed to optimize the two sub-areas with regard to the points mentioned. In order to keep the costs low, care was taken during the design phase that the components could be manufactured, if possible, with manufacturing technologies that are also available at the Res.Q Bots team's workshop or that the components could be manufactured on the FLM-system of the author of this work. At this point, too, a wide variety of methods were used to check the constructive solutions already during the construction phase by load simulations and / or rapid prototyping. In order to be able to manufacture the components internally or externally after completion of the construction, the production documents for the two sub-areas of the body and drivetrain were then created. Several offers were obtained with the production documents and attempts were also made to inspire sponsors for the project in order to keep costs as low as possible. Then the orders were triggered or the parts were manufactured by the author of this work. The most modern manufacturing technologies were used in production, such as water- and laser-cutting as well as the additive manufacturing methods of SLS- and FLM-printing. Finally, the two sub-areas as well as the entire rescue robot were assembled with the help of the Res.Q Bots team and this was handed over to the Res.Q Bots team together with the CAD-files and the development documents.

One of the key accepts of the fourth industrial revolution (called industry 4.0) is the proper usage of mobile robots, for which using an efficient motion planning algorithm is of importance. Every year, universities and educational institutes from around the world present their accomplishments in robotics within the RoboCup competitions. One of the main purposes of the rescue robots competitions is to increase the awareness of robots during their missions. This paper presents an open-source motion planning algorithm, simulated in the robot operating system (ROS) platform. The proposed planner develops a semiautonomous algorithm for the rescue robots utilized in the RoboCup competitions. The Gazebo-simulated results validate the efficient performance of the presented algorithms.

Temperature sensors with a communication capability can help monitor and report temperature values to a control station, which enables dynamic and real-time evacuation paths in fire emergencies. As compared to traditional approaches that identify a one-shot fire evacuation path, in this paper, we develop an intelligent algorithm that can identify time-aware and temperature-aware fire evacuation paths by considering temperature changes at different time slots in multi-story and multi-exit buildings. We first propose a method that can map three-dimensional multi-story multi-exit buildings into a two-dimensional graph. Then, a mathematical optimization model is proposed to capture this time-aware and temperature-aware evacuation path problem in multi-story multi-exit buildings. Six fire evacuation algorithms (BFS, SP, DBFS, TABFS, TASP and TADBFS) are proposed to identify the efficient evacuation path. The first three algorithms that do not address human temperature limit constraints can be used by rescue robots or firemen with fire-proof suits. The last three algorithms that address human temperature limit constraints can be used by evacuees in terms of total time slots and total temperature on the evacuation path. In the computational experiments, the open space building and the Taipei 101 Shopping Mall are all tested to verify the solution quality of these six algorithms. From the computational results, TABFS, TASP and TADBF identify almost the same evacuation path in open space building and the Taipei 101 Shopping Mall. BFS, SP DBFS can locate marginally better results in terms of evacuation time and total temperature on the evacuation path. When considering evacuating a group of evacuees, the computational time of the evacuation algorithm is very important in a time-limited evacuation process. Considering the extreme case of seven fires in eight emergency exits in the Taipei 101 Shopping Mall, the golden window for evacuation is 15 time slots. Only TABFS and TADBFS are applicable to evacuate 1200 people in the Taipei 101 Shopping Mall when one time slot is setting as one minute. The computational results show that the capacity limit for the Taipei 101 Shopping Mall is 800 people in the extreme case of seven fires. In this case, when the number of people in the building is less than 700, TADBFS should be adopted. When the number of people in the building is greater than 700, TABFS can evacuate more people than TADBFS. Besides identifying an efficient evacuation path, another significant contribution of this paper is to identify the best sensor density deployment at large buildings like the Taipei 101 Shopping Mall in considering the fire evacuation.

Many species in nature demonstrate symbiotic relationships leading to emergent behaviors through cooperation, which are sometimes beyond the scope of the partnerships within the same species. These symbiotic relationships are classified as mutualism, commensalism, and parasitism based on the benefit levels involved. While these partnerships are ubiquitous in nature, it is imperative to understand the benefits of collective behaviors in designing heterogeneous multi-robot systems (HMRS). In this paper, we investigate the impact of heterogeneity on the performance of HMRS applied to a search and rescue problem. The groups consisting of searchers and rescuers, varied in the individual robot behaviors with multiple degrees of functionality overlap and group compositions, demonstrating various levels of heterogeneity. We propose a new technique to measure heterogeneity in the agents through the use of Behavior Trees and use it to obtain heterogeneity informatics from our Monte Carlo simulations. The results show a positive correlation between the group's heterogeneity measure and the rescue efficiency demonstrating benefits in most of the scenarios. However, we also see cases where heterogeneity may hamper the group's abilities pointing to the need for determining the optimal heterogeneity in group required to maximally benefit from HMRS in real-world applications., Accepted for Publication at the 2020 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)

This paper mainly centers on the energy management of the medical rescue mobile robot with different payloads in the uncertain road conditions. Efficient energy usage is a crucial issue because energy consumption will increase with the application and expansion of robotics. The power consumption of the robot system is affected by the task and its operating environment. This paper designs a six-wheel-drive medical rescue mobile robot using a hybrid system. Aiming at the wheel driving conditions of mobile robots, a power-adaptation control strategy is proposed, and its structure and driving form is introduced. Firstly, based on a power-adaptation control strategy, a nonlinear model predictive control (NMPC) algorithm is proposed to optimize the power adaptive control strategy. Non-linear model predictive control uses a non-linear model to represent the medical rescue robot model and external characteristic constraints. Secondly, the AVL CRUISE module is used to build a dynamic model of a medical rescue mobile robot, and it is jointly simulated with MATLAB/Simulink to simulate the energy consumption of a medical rescue robot under Urban Driving Cycle (UDC) standard operating conditions. Finally, the NMPC method is used to solve the system and compared with the power-adaptation control strategy. The simulation results show that compared with the power adaptive control strategy, the fuel consumption of combustion engine of the NMPC is improved by 26.4%.

The mobile manipulators have become more and more popular because of its flexible operation space. However, how to protect the people on the mobile rescue robot to against the impact from unconstructed environments like the battle field or disaster is still an underexplored problem. The stability control problem is addressed in this article by devising a disturbances rejection method for medical rescue robot. We indicate that the designed method keep the posture of the end of the manipulator stable by controlling the motors of pitching direction and rolling direction. The vertical vibration can be weakened by the damping system of the rescue robot, such as spring, damper and damping materials. The wounded carried by manipulator of the rescue robot may not suffer secondary damage as the end of the manipulator always remain stable. Simulations implementations are performed to validate the proposed method and performance metric with a mobile rescuing manipulator.

In this paper, through the study and analysis of the terrain in the post-disaster area, we propose a design scheme of industrial products that can improve the efficiency of post-disaster rescue.The design combines the topography of the disaster area, existing technologies and products, and the needs of the victims to determine the product function. The appearance and internal structure of the products are determined by structural design and ergonomics. Aiming at the problem that the existing rescue products can’t overcome the complicated terrain in the disaster area, a bouncing rescue robot is proposed in this paper. At the same time, the tire size is larger than the body size to prevent damage in the fall. The equipment has a certain storage space, can carry a small amount of emergency medicine. This product is in line with the background of social medical and technological development. In the complex internal environment of disaster areas, such rescue equipment is needed to improve the efficiency of post-disaster rescue.

This paper improves visual-inertial systems to boost the localization accuracy for low-cost rescue robots. When robots traverse on rugged terrain, the performance of pose estimation suffers from big noise on the measurements of the inertial sensors due to ground contact forces, especially for low-cost sensors. Therefore, we propose \textit{Threshold}-based and \textit{Dynamic Time Warping}-based methods to detect abnormal measurements and mitigate such faults. The two methods are embedded into the popular VINS-Mono system to evaluate their performance. Experiments are performed on simulation and real robot data, which show that both methods increase the pose estimation accuracy. Moreover, the \textit{Threshold}-based method performs better when the noise is small and the \textit{Dynamic Time Warping}-based one shows greater potential on large noise., accepted by IFAC World Congress 2020

The Rapidly Manufactured Robot Challenge (RMRC) is a challenge of RoboCup Rescue Robot league that aims to develop just-in-time, custom purpose, and low-cost robots for responders to produce on the spot when disaster strikes. The RMRC robots are required be open-source hardware design using standard parts and/or 3D printed materials, and software that can be easily duplicated when needed. This paper aims to present the design of RMRC robot including hardware structure and software system. It specifically focuses on the robot design which contributed for the improvement of robot performance on complex terrain.

Odometry estimation is the problem of estimating platform pose utilizing different types of sensors. Visual odometry calculates the translation and rotation of two frames by extracting and matching feature points. However, it cannot function properly in some situations, such as dark environment or scenes with repeated textures. In rescuing scenario with poor visibility, fire-fighting robots and nuclear power plant rescue robots can not localize itself by solely depending on visual information. A real-time high precision odometry estimation method based on 6-DOF force sensors and IMU for legged robot, which can overcome the above limitations, is proposed in this paper. The odometry estimation method is realized by real-time robot posture estimation through 6-DOF force sensors mounted on the legs of legged robot. We combine particle filter and Quasi RNN network to build particle filter net. Through the fusion of 6-DOF force sensors and IMU using particle filter net, real-time odometry estimation with high precision is achieved. Compared with the state of art, our method has advantages of higher accuracy, faster computation speed and broader application scenarios for legged robot.

Semantic information has proven to be an enabling factor for robots to better understand their surroundings. In this paper, we propose an RGB-D based semantic simultaneous localization and mapping (SLAM) framework for rescue robots. By augmenting the RGB-D SLAM system with a convolutional neural network (CNN), our framework can generate not only dense geometric point-cloud maps but also corresponding point-wise semantic information (i.e. a semantic map). After obtaining the semantic map, the rescue robot can distinguish types of terrains, so as to avoid obstacles and find out paths with higher traversability. On the one hand, we utilize depth information to determine whether neighboring pixels in semantic images belong to the same object, so as to filter the segmentation results of each frame. On the other hand, we filter the semantic map by accumulating data of multiple frames and searching consistent semantic labels. To validate the efficiency of the proposed semantic SLAM framework, we generate an RGB-D dataset of the RoboCup Rescue-Robot-League (RRL) competition environment. The experiment proves that our semantic SLAM framework can generate dense and accurate semantic maps for the complex RRL competition environment.

Robotic systems bring significant support in search and rescue missions, especially in disastrous scenarios that harbor significant dangers for rescue forces. In these hazardous areas, remote-controlled rescue robot systems can provide a fast and yet secure way to scout the area and discover survivors. These evolving systems must be tested extensively in various reproducible setups before real-world deployment. Their performance in communication constrained environments, which often induce degrading and even missing network links, is of worth. Therefore, this work presents a concept for an evaluation platform following a Hardware in the Simulation Loop (HiSL) approach to test robotic applications in challenging network environments as well as evaluate communication solutions developed for rescue robotics. An exemplary implementation of the platform concept is provided, which uses extensive raytracing simulations to generate coverage maps of rescue scenarios defined in ROS/Gazebo. These maps are used to simulate the performance of real communication systems. The platform concept implementation is used in a case study based on a sample scenario from the DARPA Subterranean (SubT) challenge, to evaluate SKATES, a communication module of our conception, in its ability to provide reliable network access by leveraging its Multi-Connectivity feature. Results demonstrate the fidelity of the communication behavior in the real-world to the constraints established by the communication environment in the simulation, as well as the robust network behavior of the Multi-Radio Access Technology (Multi-RAT) enabled SKATES module.

ImPACT Tough Robotics Challenge is a national project of Japan Cabinet Office that focuses on tough technologies of robotics to give solutions to disaster response, recovery and preparedness. Natural and man-made disasters are a serious problem for our society. Robotics is widely recognized as potentially effective countermeasure to solve this problem. It has, however, limited capability due to the fragility of this technology. Many robot technologies can work only under well-prepared conditions, which do not occur in disaster sites. This project aims at making such technologies tougher by removing constraints. It consists of subprojects of six types of robot platforms and several component technologies integrated with the robots: Cyber Rescue Canine, digitally empowered rescue dogs, serpentine robots for search in debris, serpentine robots for plant/infrastructure inspection, UAVs for gathering information in wide area of disaster area, legged robots for plant/infrastructure inspection in risky places, construction robots for recovery tasks that require both high-power and preciseness. This key speech introduces some of the major research outcomes of this project.

This paper focuses on the teaming aspects and the role of heterogeneity in a multi-robot system applied to robot-aided urban search and rescue (USAR) missions. We propose a needs-driven multi-robot cooperation mechanism represented through a Behavior Tree structure and evaluate the system's performance in terms of the group utility and energy cost to achieve the rescue mission in a limited time. From the theoretical analysis, we prove that the needs-driven cooperation in a heterogeneous robot system enables higher group utility than a homogeneous robot system. We also perform simulation experiments to verify the proposed needs-driven collaboration and show that the heterogeneous multi-robot cooperation can achieve better performance and increase system robustness by reducing uncertainty in task execution. Finally, we discuss the application to human-robot teaming., This is the final version accepted by the 2020 International Symposium on Safety, Security and Rescue Robotics (SSRR 2020)

For traversing uneven terrain in degraded environments, determining the static stability and consequently the tip-over risk of a mobile ground rescue robot is fundamental for planning and evaluation of paths. This paper presents a novel iterative geometric method that reduces the problem of robot pose prediction to two-dimensional image-processing operations by introducing the concept of a robot heightmap. The presented method requires only geometrical and mass information extracted from the widely used unified robot description format (URDF) to compute the robot heightmap, which makes it transferable to a wide range of mobile robot platforms without modification. We demonstrate that the approach accurately predicts the real robot's 6D pose at the input x-y-coordinates. Runtimes allowing the evaluation of poses in the order of ten thousand poses per second show that the method is computationally efficient enough to be used in online path planning.

Visual object recognition is a fundamental challenge for reliable search and rescue (SAR) robots, where vision can be limited by lighting and other harsh environmental conditions in disaster sites. The goal of this paper is to explore the use of thermal and visible light images for automatic object detection in SAR scenes. With this purpose, we have used a new dataset consisting of pairs of thermal infrared (TIR) and visible (RGB) video sequences captured from an all-terrain vehicle moving through several realistic SAR exercises participated by actual first response organisations. Two instances of the open source YOLOv3 convolutional neural network (CNN) architecture are trained from annotated sets of RGB and TIR images, respectively. In particular, frames are labelled with four representative classes in SAR scenes comprising both persons civilian and first-responder) and vehicles (Civilian-car and response-vehicle). Furthermore, we perform a comparative evaluation of these networks that can provide insight for future RGB/TIR fusion. This work has been done in the framework of the TRUST-ROB project, funded by the Spanish Government (RTI2018-093421-B-I00). Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.

In the age of modern technological capabilities, robotic systems play a vital role in making our lives more comfortable. Robotic systems are becoming an essential part of human life due to their efficiency, multi-functionality, and high performance. In recent years, search and rescue robot systems are used tremendously for helping to rescuers in a natural disaster. Every year, millions of people are affected by disasters in different parts of the world. Disasters can be manmade or natural, such as building collapse, earthquakes, avalanches, volcanic activity, wildfires, and floods, etc. This witnesses the importance of sensor-based search and rescue robot systems in the emergency and also disaster management field. A variety of sensing and wireless technologies are used for remote and vision controlling in the emergency field. The use of these sensing and wireless technologies, the rescuers instead of going inside in the disaster area, can control the robot systems remotely when calamity occurs. A remote controller is used in the remote control of modern robotic systems. In this paper, we design an analog sensing and Leap Motion integrated remote controller for search and rescue robot system. The controller consists of an Arduino Mega Pro MINI, joystick module, Leap Motion controller, radio module, USB hub, potentiometer, power switch, button, USB type B female, Ii-on battery and Ii-on charger. The remote controller has the ability to help the rescuers to remote control in the disaster area from far away. The rescuers also could save their lives by using this remote controller. The main objective of this paper is to design a multi-functional and easy to control remote controller for search and rescue robot system.

Ideally, search and rescue operations after a natural disaster has struck, should be performed by search and rescue robots. As natural disasters strike in very different environments and terrains, all-terrain robots are the best choice. By taking inspiration from salamanders, an amphibian, which can both swim and walk, we propose a new leg mechanism for uneven terrains. The mechanism is fabricated using commercial 3D printers, making them cheap, and illustrating how accessible 3D printers can be used for mechanism design. The feasibility of our approach is tested in practice.

Balancing is one of the most essential ability for legged robots. From maintaining posture on unstable surfaces to withstanding sudden force disturbances, balancing is widely used in rescue robots. Among these various balancing issues, this study focused on balancing on moving plates. The study is applicable when the robot needs to perform an operation on an earthquake or shaking ship environment. In addition, since ZMP(Zero Moment Point) is used for the control, the performance is exhibited not only when an external force is applied such as wind force, but also an inertial force is exerted. In this study, reinforcement learning was used so that the proposed algorithm can avoid redundancy issues and kinematic singularities which cause problems in traditional method. The simulation results show how this new approach can improve the robot’s balancing ability.

Chemical disaster events are characterized by suddenness, danger and variability, while robots are inefficient and unsafe in path planning and task allocation under special and blocked chemical environment. In order to improve rescue speed and safety, combining the characteristics of the environment, a task framework for rescue robots is proposed in the paper. The improved ant colony algorithm is used to obtain the shortest path plan. The result of the shortest path is used in the task allocation process. A task allocation model with the goal of minimum time is proposed and solved by genetic algorithm with elite strategy (EGA). The simulation results show that the method proposed in this paper can be well adapted to the chemical disaster environment, and provides a better or sub-optimal solution for the task allocation problem of rescue robots.

Explainable Artificial Intelligence (XAI) systems, including intelligent agents, must be able to explain their internal decisions, behaviours and reasoning that produce their choices to the humans (or other systems) with which they interact. In this paper, we focus on how an extended model of BDI (Beliefs-Desires-Intentions) agents can be able to generate explanations about their reasoning, specifically, about the goals he decides to commit to. Our proposal is based on argumentation theory, we use arguments to represent the reasons that lead an agent to make a decision and use argumentation semantics to determine acceptable arguments (reasons). We propose two types of explanations: the partial one and the complete one. We apply our proposal to a scenario of rescue robots., 9 pages, accepted in the 7th Brazilian Conference on Intelligent Systems, 2019

Personnel search and rescue work is a kind of emergency rescue work mainly to save the lives of personnel. If only firefighters carry out search in unknown areas in the field, the efficiency is too low and it is easy to delay the best rescue time. If a joint search is carried out using mobile robots and firefighters, it will be beneficial to find missing persons with vital signs in a timely manner, and it will be convenient to soothe the emotions of family members in a timely manner, embodying the humanistic care and humanitarian spirit. In order to solve the problem that the current rescue robot has high energy consumption and short flight time, and can not undertake a large number of long-time search and rescue tasks. This project proposes a multi-robot collaborative search and rescue system based on renewable energy to extend the mobile robot's battery life, this system is mainly divided into five parts: new solar system, search and rescue robot, Internet of Things networking, cloud server, and WeChat applet. At the same time, Multiple robots carry out collaborative search and rescue operations through the ZigBee wireless network, and the camera carried by a single robot can identify the human body with edge computing. After networking, the 4G mobile network is used to send the personnel recognition results to the background terminal, to indicate if a missing person was found. Considering that the efficiency and accuracy of searching need to be improved urgently, an improved golden section method is proposed to keep the output power of the solar panel at the highest level to increase flight duration. This project meets the urgent needs of high-efficiency rescue, energy conservation and environmental protection.

Providing vision to robots has been an effective application in the field of robotics which enhanced automation. There have been several algorithms developed in recent times for object recognition and YOLO v3 which is one of the best has shown very good results in real-time object recognition. Consequently, the same has been chosen for this research. This research aims at developing a vision based autonomous manipulation system for assistive applications such as service robots, rescue robots, wheelchairs, etc. A detailed system integration between vision and robotic arm using the Robot Operating System (ROS) framework has been presented. This paper also explains the method of coordinate transformation between camera and manipulator reference systems and the results are discussed.

In this era of a politically unstable world, there is a growing demand for the use of military robots to aid the soldiers to perform perilous missions. This paper focuses on the design and build of a semi-autonomous, unmanned robotic system used for various military and rescue operations. Dangerous tasks such as bomb disposal, enemy territory surveillance, search and rescue can be efficiently carried out by the MSRR, Military Support and Rescue Robot. This reduces the risk of losing the lives of both soldiers and civilians. With the help of live feed from the wireless camera and data analysis of environmental composition by various sensors, of the area under surveillance, the soldiers can better prepare for their missions. Using Arduino and Zigbee technology, the above-mentioned tasks can be achieved. The different sensors and the robotic arm are connected to the Arduino mega which in turn is connected to the Zigbee. Data transmission and receiving are through Zigbee technology. This prototype design overcomes the weakness of the existing models and thus provides better support for military operations.

In recent years, the development and deployment of autonomous systems such as mobile robots have been increasingly common. Investigating and implementing ethical considerations such as fairness in autonomous systems is an important problem that is receiving increased attention, both because of recent findings of their potential undesired impacts and a related surge in ethical principles and guidelines. In this paper we take a new approach to considering fairness in the design of autonomous systems: we examine fairness by obtaining formal definitions, applying them to a system, and simulating system deployment in order to anticipate challenges. We undertake this analysis in the context of the particular technical problem of robot navigation. We start by showing that there is a fairness dimension to robot navigation, and we then collect and translate several formal definitions of distributive justice into the navigation planning domain. We use a walkthrough example of a rescue robot to bring out design choices and issues that arise during the development of a fair system. We discuss indirect discrimination, fairness-efficiency trade-offs, the existence of counter-productive fairness definitions, privacy and other issues. Finally, we elaborate on important aspects of a research agenda and reflect on the adequacy of our methodology in this paper as a general approach to responsible innovation in autonomous systems.