Showing papers on "Rescue robot published in 2003"

Human-robot interactions during the robot-assisted urban search and rescue response at the World Trade Center

Abstract: The World Trade Center (WTC) rescue response provided an unfortunate opportunity to study the human-robot interactions (HRI) during a real unstaged rescue for the first time. A post-hoc analysis was performed on the data collected during the response, which resulted in 17 findings on the impact of the environment and conditions on the HRI: the skills displayed and needed by robots and humans, the details of the Urban Search and Rescue (USAR) task, the social informatics in the USAR domain, and what information is communicated at what time. The results of this work impact the field of robotics by providing a case study for HRI in USAR drawn from an unstaged USAR effort. Eleven recommendations are made based on the findings that impact the robotics, computer science, engineering, psychology, and rescue fields. These recommendations call for group organization and user confidence studies, more research into perceptual and assistive interfaces, and formal models of the state of the robot, state of the world, and information as to what has been observed.

Evolution of a Performance Metric for Urban Search and Rescue Robots (2003)

Abstract: : This paper discusses the advancement and proliferation of the Reference Test Arenas for Urban Search and Rescue Robots as representative search and rescue environments, which allow objective performance evaluation of mobile robot capabilities. These arenas have hosted annual rescue robot competitions sponsored by the American Association for Artificial Intelligence since 2000 and the RoboCupRescue Robot League since 2001. The rules of these competitions have evolved each year to encourage robots to negotiate complex and collapsed structures, find simulated victims, determine their condition and location, and generate human readable maps to enable victim recovery. The associated performance metric has also evolved as it attempts to quantify and encourage these and other robot capabilities pertinent to urban search and rescue applications. This paper presents the competition rules, performance metric, and generalized results of the 2003 competitions which included some inspiring robotic implementations. Performance data captured during these competitions is discussed along with recently available development tools which can quicken the pace of innovation in the field of search and rescue robotics.

Rescue robot under disaster situation: position acquisition with Omni-directional Sensor

Abstract: This paper proposes a network system and an algorithm for a rescue robot to obtain its position under collapsed area. The network system consists of communication tags put dynamically by the rescue robot in its rescue activities. According to the temporary tags, the system constructs temporary communication infrastructure and obtains geometrical information of the area. In particular, to get the position of the rescue robot, our algorithm employs "angle" obtained from Omni-directional Sensor mounted on the communication tag. The use of the "angle" information leads a significant decrease in the error in estimating tags' location. In this paper, the feasibility of our system and algorithm is confirmed with the simulation.

RoboCup 2002 : Robot Soccer World Cup VI

Abstract: An Overview of RoboCup 2002 Fukuoka/Busan.- Technical Papers.- Constraint-Based Landmark Localization.- Improving Vision-Based Self-localization.- Evaluation of Self-localization Performance for a Local Vision Robot in the Small Size League.- Fast Image Processing and Flexible Path Generation System for RoboCup Small Size League.- A Modified Potential Fields Method for Robot Navigation Applied to Dribbling in Robotic Soccer.- Using Online Learning to Analyze the Opponent's Behavior.- Hidden Markov Modeling of Multi-agent Systems and Its Learning Method.- Learning the Sequential Coordinated Behavior of Teams from Observations.- Towards a Life-Long Learning Soccer Agent.- Adaptive Synchronisation for a RoboCup Agent.- Team Formation for Reformation in Multiagent Domains Like RoboCupRescue.- MPADES: Middleware for Parallel Agent Discrete Event Simulation.- Towards RoboCup without Color Labeling.- Integration of Advice in an Action-Selection Architecture.- The Role of Motion Dynamics in the Design, Control and Stability of Bipedal and Quadrupedal Robots.- Multiagent Competitions and Research: Lessons from RoboCup and TAC.- RoboCupJunior: Learning with Educational Robotics.- Posters.- A Rescue Robot Control Architecture Ensuring Safe Semi-autonomous Operation.- A Framework for Learning from Observation Using Primitives.- Robosoccer-RU Open Simulation League: Principles and Algorithms.- An Interactive Software Environment for Gait Generation and Control Design of Sony Legged Robots.- Real-Time Randomized Path Planning for Robot Navigation.- Towards an Optimal Scoring Policy for Simulated Soccer Agents.- Decision-Making and Tactical Behavior with Potential Fields.- Localization of Robots in F180 League Using Projective Geometry.- Reinforcement Learning in Large State Spaces.- Co-evolution of Morphology and Controller for Biped Humanoid Robot.- Towards Real-Time Strategic Teamwork: A RoboCup Case Study.- MUREA: A MUlti-Resolution Evidence Accumulation Method for Robot Localization in Known Environments.- Direct Reward and Indirect Reward in Multi-agent Reinforcement Learning.- Relating the Entropy of Joint Beliefs to Multi-agent Coordination.- Real-Time Decision Making under Uncertainty of Self-localization Results.- KiRo - An Autonomous Table Soccer Player.- Adaptive Methods to Improve Self-localization in Robot Soccer.- Team Coordination among Robotic Soccer Players.- An Architecture for a National RoboCup Team.- Probabilistic Vision-Based Opponent Tracking in Robot Soccer.- Behavior Acquisition Based on Multi-module Learning System in Multi-agent Environment.- League Reports.- Simulation League - League Summary.- RoboCup 2002 Small-Size League Review.- Medium Size League: 2002 Assessment and Achievements.- Sony Four Legged Robot League at RoboCup 2002.- RoboCupRescue Simulation League.- RoboCupRescue Robot League.- Lessons Learned from Fukuoka 2002 Humanoid League.- RoboCupJunior 2002: The State of the League.

Constructing a 3-D map of rubble by teleoperated mobile robots with a motion canceling camera system

Abstract: In order to search and rescue the victims in rubble effectively, a 3-D map of the rubble is required. As a part of the national project of rescue robot system, we are investigating a method for constructing a 3-D map of rubble by teleoperated mobile robots. We are also planning to build an intuitive user interface for teleoperating robots and navigating in a virtualized rubble model using the obtained 3-D model. In this paper, some preliminary research results are introduced. We did some design studies of laser range finders that can be mounted on a mobile robot and can get the range data of the rubble around the robot. Then, we formulated a 3D SLAM (Simultaneous Localization and Map Building) algorithm and conducted some simulation studies. Lastly, we proposed a novel motion canceling camera system and confirmed its validity by experiment.

Motion algorithm for autonomous rescue agents based on information assistance system

Abstract: In this paper, we propose an information assistance system and an algorithm for distributed rescue agents to improve their rescue activities. To save victims, finding them is quite important. We introduce a small intelligent device called "intelligent data carrier for rescue (IDC-R)" and a mediator blimp in order to search victims. Then, we propose an algorithm for distributed rescue agents to visit them, which needs few calculation cost. We verify the effectiveness by carrying out simulations.

Building better swarms through competition: lessons learned from the AAAI/RoboCup Rescue Robot competition

Abstract: A common problem in a disaster situation, whether man-made or natural, is the need to quickly identify locations of potential victims and potential hazards to human rescuers, with minimal personnel on site at the beginning of the emergency. Robots can be used to supplement available personnel and to assist them in their search. However, it is important that the robots used not pose a danger to rescuers and victims through collisions or causing structural collapse and that they not get in the way of rescue efforts. Another problem in a disaster area is that environmental conditions (e.g., rubble, scrap metal, dust, smoke, and fire) can make it difficult for robots to maneuver, reduce effectiveness of sensors, and hamper communications. We believe the best approach to developing an effective robotic assistant to human rescue teams is through swarms of low-cost, small robots. The robots should be low cost to eliminate concerns about not recovering them after a disaster. They should be small so they don't hinder or pose a risk to humans (rescuers can kick them or step on them if they are in the way and they will be too small to move objects or injure a person through collision). And we believe a swarm should be used to maximize the area covered while maintaining enough contact between robots to maintain a reliable communications link. A swarm of small robots programmed with simple behaviors can achieve these goals while keeping costs down. This paper describes the efforts we have undertaken at Utah State University in developing urban search and rescue robot swarms for the American Association for Artificial Intelligence and RoboCup Rescue Robot competitions. Both of these competitions make use of the standard urban search and rescue test course developed by the National Institute of Standards and Technology (NIST). Our initial efforts to try to determine the bare minimum competence required for a rescue swarm are described, as are our efforts to improve communications between robots and a base station. Our current efforts to implement a flocking behavior in a robot swarm are described, as is the most recent modular, behavioral robot design we are working on. The development of a graphical user interface for use by rescuers to interface with the swarm is also described. Finally, we discuss the direction we think this research needs to take in the future.

The concept and research of a pipe crawling rescue robot

Abstract: This paper presents the control algorithm and design of a pipe crawling robot which can be used for the purpose of earthquake rescue and pipeline maintenance. The robot is designed to be able to in...

Adaptive mobility for rescue robots

Abstract: It has often been observed that the most daunting aspect of any crisis response is managing the "unknown unknowns" that inevitably plague incident commanders and emergency personnel at all levels responsible for life and death decisions on a minute by minute basis. In structural collapse situations, for example, rescue crews rarely have even a coarse picture of the number or disposition of people or material scattered amongst the twisted beams and piles of concrete that typically entomb would-be survivors. How can the incident commander decide which beam to lift or even which section of the building to search first in the absence of information of what lies beneath. Even the slightest tug on a concrete slab can collapse potential life harboring void spaces below killing potential survivors in the process. In deploying mobile robots to assist in rescue operations we combined the traditional advantages of machine immunity to fatigue, hazardous materials and environmental controls, with the mechanical design freedom that allowed small platforms to penetrate deep into rubble to expand both situational awareness and operational influence of rescue services at the World Trade Center and mountainous snow-bound caves in Afghanistan. We learned a great deal from these experiences with regard to robot emloyment and design. This paper endeavors to share a few of our more prominent lessons learned regarding portable robot mobility as a means to manage user expectations and stimulate more innovative and adaptive design.

Adaptation of rescue robot behaviour in unknown terrains based on stochastic and fuzzy logic approaches

Abstract: The purpose of this article is to provide rescue robots with an adaptive behaviour during searching for victims in disasters such as fire, earthquake, flood, wars etc. This experimental research work took place in previously unknown dynamic indoor terrains. The main phases of this framework are; 1) modelling of robot behaviours/dynamics in collapsed environments, 2) designing an adaptive controller, which regulates robot longitudinal velocity and heading (collision avoidance) based on the obstacles distribution histogram, 3) prediction of robot behaviours in another unknown terrain. Two approaches have been used to design the adaptive controller: the first one is the stochastic control theory, based on Kalman filter algorithms. The second approach relies on fuzzy inference systems (FIS). Throughout this work, robot dynamics have been modelled using the auto regressive exogenous (ARX) scheme, while ARX model parameters have been identified using recursive least squares (RLS). This contribution presents a description and some discussion of the discrete Kalman filter, modelling techniques, and some discussion of robot behaviour analysis. Furthermore, the design of adaptive controllers using FIS-based techniques versus stochastic control systems bas been demonstrated.

Evaluation of the Scout Robot for Urban Search and Rescue

Abstract: A group of miniature mobile robots called Scouts were tested in the Urban Search and Rescue (USAR) course used in the RoboCup Rescue competition at IJCAI 2001. This testing was to evaluate the utility of using small robots with limited mobility and sensing constraints in the unstructured and chaotic environments present in disaster areas where USAR operations are required. The Scouts and their performance in the course are described. Finally, potential areas of future work that were revealed by these tests are discussed.

The bristle theory and traction experiment of a brush based rescue robot

Abstract: This work introduces the concept of a brush-based tractor used for rescue in collapsed buildings or tunnels. The paper presents the bristle theory and traction experiments relating to a robot, which uses a sensor system for detecting the shapes of pipes or tunnel like voids within rubble. Traction experiments in the laboratory were used to investigate the characteristics of bristles and the performance of the brush units of different shapes. The experimental results are discussed in the paper and related to a single bristle theory with a view to giving guidance for the design of a future brush based rescue robot in debris.

Blue Swarm 2.5 A Step Toward an Autonomous Swarm of Search and Rescue Robots

Abstract: Urban search and rescue is a difficult domain for autonomous mobile robots to operate in. The environment can be expected to be highly unstructured, with many obstacles and hazards for a robot to deal with. In addition, if human rescue teams are going to accept robotic assistance, they need to be assured that the robots are going to be helpful, not a hindrance. With these factors in mind, we have been working toward the development of an autonomous swarm of small, inexpensive search and rescue robots. The robots should be autonomous in order to provide useful information to human rescuers without requiring specialized knowledge in operating robots. A swarm is useful because it allows for losses of individual robots and for redundant communications pathways, without losing overall effectiveness of the swarm. The robots should be small so they will not pose a danger to rescuers or the victims being searched for. And they should be inexpensive because worrying about the loss of robots should not be a consideration for human rescuers. Blue Swarm 2.5 is the latest incarnation in our quest for an autonomous rescue robot swarm. This paper describes our efforts to develop an effective rescue robot swarm. The paper starts by describing the past incarnations of the swarm, including the research objectives being pursued and the results obtained. Then the most recent version of the swarm, Blue Swarm 2.5, is described. Finally, the plans for Blue Swarm 3, the first fully functional rescue swarm, will be described.

Rescue robot system

Abstract: PROBLEM TO BE SOLVED: To carry out an injured person to a safety place in a disaster scene where a person hardly approaches such as a disaster scene in a nuclear-related facility having the possibility of being exposed to a radiation SOLUTION: This rescue robot system is equipped with a plurality of robots 15 loading respectively a bag member 3 capable of filling inside liquid material or particulate material The robot can select a mode of autonomous travel or remote manual travel Each bag member is connected to a hose 2 and a pipe 4, and the pipe and the hose are connected together by a pair of connectors which is a connection means The liquid material or the particulate material is supplied to the connected bag member by using a pump COPYRIGHT: (C)2003,JPO

The AAAI-2002 Robot rescue

Abstract: The purpose of the AAAI-2002 Robot Rescue event is to challenge researchers to design useful robotic systems for urban search and rescue (USAR). The competition rules are written to simulate a real rescue response in a simulated disaster environment developed by the National Institute of Standards and Technology. This article provides an overview of the current state of the art for USAR robotics, an overview of the AAAI-2002 Robot Rescue event, and a discussion of the future of the Robot Rescue event.

A remote measurement method of the human biosignals

Abstract: The big earthquake will produce many sufferers. Rescue robots which help sufferers are developing in various laboratories. And it is very important for rescue team to grasp sufferer's condition. If it is possible to know them, we can decide order to rescue and take suitable treatment after rescues. And a lot of life of the sufferers will be saved. It seems that it is difficult for the rescue team to approach the sufferer at the disaster. Therefore, in the disaster area, the measurement of the sufferer's bio-signals should be taken by remote sensing or easy contact. Our objective of this study is the development of the bio-signal sensors which can be set on the small rescue robot for this kind of measurement. In this paper, we will talk about our developed sensors which can measure respiratory rate and pulse rate.

Flat-distributed network architecture (FDNet) for rescue robots

Abstract: This paper deals with the software architecture of a rescue robot, named FDNet. This architecture provides the rescue robot with intelligence and flexibility. When this architecture is used, the robot system is described using networks. These networks are composed by data and processing units. The data, referred to as "data", is a distributed component. The processing units, referred to as "relation", are a distributed and parallel-processing component, which can refer to any existing Data. We consider nodes that can formally connect to any other node, and relations that can be organized according to human's or any other network's pattern. This architecture was called FDNet (flat-distributed networks for rescue robots). We describe proposition of the architecture and its implementation for a robot. Then, we report some experimental results. We provide this architecture for any intelligent rescue system.

Tracking trajectory planning for disaster response multiple mobile robots: numerical simulation study

Abstract: Fire fighting and rescue activity needs much manpower. Moreover, fire fighters and rescue company members face risky situation. Therefore they are good and suitable subject for robots development. Then, we discuss the effectiveness of accident response robots and rescue robots from its size and configuration. We resulted to that a small mobile robot group is the one of the effective system for rescue robot in accidents. The mobile robots group needs to move from safety area to accident site or danger field first. There has already developed some leading-following system. However there was no consideration for accidental situation and circumstance. Therefore we propose a tracking trajectory planning method that is useful for the mobile robots group against accidents. Furthermore, we carried out numerical simulation to confirm the performance of the method. Finally, we conclude the tracking trajectory planning method that we proposed is useful for small mobile robot group for accident response based on the results of numerical simulations.

A Consideration on Rescue Robot Contest from Viewpoint of Technology Education

Abstract: Many robot contests have been widely held for the purpose of training of creativity through the production education. In this paper, various robot contests are first cosidered from the viewpoint of technology education including the production education, and show the validity and some problems. Furthermore, the rescue robot contest is also considered from the viewpoint of technology education, and the difference between the rescue robot contest and other robot contests is clarified. Finally, some rescue robots designed by Hiroshima Univ. team and the rescue strategies are introduced. 1.緒 言 平成7年1月17日に発生した阪神・淡路大震 災以降,レスキュー活動に関する研究が盛んに行 われるようになった。また,本年度からは文部科 学省大都市大震災軽減化特別プロジェクトも立ち 上がり,研究活動が本格化されてきた。その一方 で,レスキュー活動やレスキュー技術の啓蒙を目 的として,レスキューロボットコンテスト1)が 2年前から開催されている(プレ大会を含めると 3年前からの開催)。このコンテストは1/8ス ケールで模擬したフィールド(震災現場)から, ダミー人形(ダミヤン)を迅速に放出し,安全ゾ ーンに搬送することを競うロボットコンテストの 一つである。その際,被災者の立場,いわゆる人 道的立場に立った救出方法が求められており,こ の点についてのアイデアも評価の対象となってい m 一方,さまざまなロボットコンテストが,全国 各地で開催されるようになってきた。最も有名な ところでは, NHKアイデア対決ロボットコンテス ト2)が,およそ10年くらい前から開催されてお り,ものづくり教育の促進において一役を担って いる。しかし,これら多くのロボットコンテスト は,創意工夫する能力の育成や論理的な思考能力 の育成など,いわゆる創造力の育成という観点で は一応の成果を収めてはいるものの,コンテスト での勝敗に重点が置かれるあまり, 「相手への思 いやり」や「人との協調性」など,さらに一歩踏 み込んだメンタル的な部分の育成という点が,十 分に考慮されていないように思われる。技術教育 においては, 「ものづくり教育は人づくり」とい う考えのもと,ものづくり教育を通して人間形成 というより深い内容が扱われている。 本稿では,まず,さまざまなロボットコンテス トをものづくり教育を含めた技術教育の側面から 眺め,その有効性と問題点について考察する。次 に,レスキューロボットコンテストを先と同様に 技術教育の観点から考察し,他のロボットコンテ ストとの違いを明らかにする。最後に,レスキュ ーロボットコンテストに向けて製作したロボット と,コンテストの模様を紹介する。 *呉工業高等専門学校, **高松工業高等専門学校

Flat-distributed network architecture (FDNet) for rescue robots - FDNet and its implementation

Abstract: This paper deals with flat-distributed architecture for a rescue robot. This architecture provides the rescue robot with intelligence and flexibility. When this architecture is used, the robot system is described using networks. These networks are composed by data and processing agents. The data, referred to as "data", is a distributed component. The processing agents, referred to as "relation", are a distributed and parallel-processing component, which can refer to any existing data. We consider nodes that can formally connect to any other node, and relations that can be organized according to human's or any other network's pattern. This architecture was called "FDNet(Flat-Distributed Networks for Rescue System)". First, we describe the proposition of the architecture and its implementation for a robot. Then we report some experimental results. We provide this architecture for any intelligent rescue system.