A framework for area coverage and the visual search for victims in USAR with a mobile robot
01 Nov 2010-pp 112-118
TL;DR: A framework developed to imbue a mobile robot with the intelligence to perform the search task under the guidance of a human supervisor is presented, which enables the robot to perform area coverage as well as to search of victims visually using computer vision.
Abstract: Mobile robots can serve to augment the capabilities of rescuers for urban search and rescue (USAR) situations but must be supervised by humans. As such, the envisioned application for this research is to deploy a human-supervised mobile robot to perform the search aspect of a USAR mission. This paper presents a framework developed to imbue a mobile robot with the intelligence to perform the search task under the guidance of a human supervisor. The framework enables the robot to perform area coverage as well as to search of victims visually using computer vision. Preliminary experiments to test the framework are also described. We find that the framework is suitable for implementation on a mobile robot for its envisioned purpose.
Citations
More filters
TL;DR: A distributed approach to coordinate a team of heterogeneous UAVs cooperating efficiently in patrolling missions around irregular areas, with low communication ranges and memory storage requirements, which can be used with small-scale UAV's with limited and different capabilities.
Abstract: Using aerial robots in area coverage applications is an emerging topic. These applications need a coverage path planning algorithm and a coordinated patrolling plan. This paper proposes a distribut...
67 citations
28 May 2013
TL;DR: Sufficient and necessary conditions are provided to guarantee one-to-one UAV communication in grid-shape area partitions, allowing to share any new information among all the members of the team, even under strong communication constraints.
Abstract: This paper presents the decentralized strategy followed to ensure information propagation in area monitoring missions with a fleet of heterogeneous UAVs with limited communication range The goal of the team is to detect pollution sources over a large area as soon as possible Hence the elapsed time between two consecutive visits should be minimized On the other hand, in order to exploit the capabilities derived from having a fleet of UAVs, an efficient area partition is performed in a distributed manner using a one-to-one coordination schema according to the limited communication ranges Another requirement is to have the whole team informed about the location of the new pollution sources detected This requirement is challenging because the communication range of the vehicles is small compared to the area covered in the mission Sufficient and necessary conditions are provided to guarantee one-to-one UAV communication in grid-shape area partitions, allowing to share any new information among all the members of the team, even under strong communication constraints The proposed decentralized strategy has been simulated to confirm that fulfils all the goals and requirements and has been also compared to other patrolling strategies
39 citations
Cites background from "A framework for area coverage and t..."
...2) Two new polygons: P1 = [P (links[1] : links[2]);u] P2 = [P (links[2] : links[3]);u] can be defined using a point u interior to P , such that: A(P1) = Ai/4 A(P2) = Ai/4 u ∈ P 3) Given the polygon V = [P (links[3] : links[4]);u]:...
[...]
...Monitoring missions have been widely studied in different contexts [1], [2]: automated inspection, search and rescue missions, planetary explorations, etc....
[...]
21 Jun 2017
TL;DR: An innovative assistive system for victims' localization under an Urban Search and Rescue environment that exploits miniaturized Long Wave Infrared cameras and algorithms properly combined with template matching schemes from visual cues is proposed.
Abstract: In this paper, we propose an innovative assistive system for victims' localization under an Urban Search and Rescue environment. The localization exploits miniaturized Long Wave Infrared (LWIR) cameras and algorithms properly combined with template matching schemes from visual cues. The approach first thresholds the data to roughly estimate alive victims' location and then apply a segmentation scheme to improve the probability analysis. The key challenge of our approach is the fact the thermal image used captures images at very low resolution. This selection is necessary so that the sensor is light and thus able to be carried out by a snake robot. Experiments are presented to demonstrate the efficiency of our results both at the laboratory and under real-life conditions. The latter have been conducted under the aegis of FP7-INACHUS European Union funded project
20 citations
Book•
01 Jan 2015
TL;DR: A general overview of path planning and trajectory planning algorithms can be found in this article, where an overview of real-time and off-line planning strategies for robotic manipulation of unknown objects is presented.
Abstract: Path-Planning and Trajectory-Planning Algorithms: A General Overview.- Off Line and Real Time Planning Strategies.- Grasping and Manipulation of Unknown Objects Based on Visual and Tactile Feedback.- Obstacle Avoidance with Industrial Robots.- Planning Automatic Surgical Tasks for a Robot Assistant.- Motion Planning Using Fast Marching Squared Method.- Car-like Robots Maneuver Generation.- Motion Planning of a Spherical Mobile Robots.- Online Walking Pattern Generation Using FFT for Humanoid Robots.- Hexapod Walking Robot Locomotion.- Robotic Manipulation within the Underwater Mission Planning Context: A Use Case for Benchmarking.
18 citations
29 Jun 2016
TL;DR: A system suitable to perform precise and fast earthquake's survivor detection using a miniaturized Long Wave Infrared (LWIR) camera is described and research is carried out to implement feature descriptors for detecting only parts of partly occluded people (arms, etc.) in order to reduce false positive ratio.
Abstract: In this paper a system suitable to perform precise and fast earthquake's survivor detection using a miniaturized Long Wave Infrared (LWIR) camera is described. Main challenge of this work is the detection environment which may be characterized by smoke, dust, rubble and extremely narrow spaces as well as the extremely low resolution of the continuous moving LWIR camera. To this direction the thermal information received by the LWIR camera is exploited. In addition, research is carried out in order to implement feature descriptors for detecting only parts of partly occluded people (arms, etc.) in order to reduce false positive ratio. The proposed system achieves real time earthquake's survivor detection using a miniaturized LWIR camera. The results have been tested and evaluated in real life conditions using two different LWIR cameras for proving the robustness and the accuracy of the developed system.
12 citations
Cites methods from "A framework for area coverage and t..."
...For survivor detection and localization applications, LWIR cameras have been installed in order to compare temperature values and estimate victims [8] [9][10]....
[...]
References
More filters
Book•
01 Oct 1991TL;DR: In this article, the authors introduce engineering psychology and human performance, and present an overview of the major aspects of engineering psychology, including: Signal Detection, Information Theory and Absolute Judgment, Attention in Perception and Display Space, Spatial Displays, Memory and Training 8. Decision Making 9. Selection of Action 10. Attention, Time sharing and Workload 11. Mental Workload, Stress, and Individual Differences: Cognitive and Neuroergonomic Perspectives 12. Automation 13. Epilogue
Abstract: 1. Introduction to Engineering Psychology and Human Performance 2. Signal Detection, Information Theory and Absolute Judgment 3. Attention in Perception and Display Space 4. Spatial Displays 5. Spatial Cognition, Navigation and Manual Control 6. Language and Communications 7. Memory and Training 8. Decision Making 9. Selection of Action 10. Attention, Time sharing and Workload 11. Mental Workload, Stress, and Individual Differences: Cognitive and Neuroergonomic Perspectives 12. Automation 13. Epilogue
5,366 citations
TL;DR: This paper surveys recent results in coverage path planning, a new path planning approach that determines a path for a robot to pass over all points in its free space, and organizes the coverage algorithms into heuristic, approximate, partial-approximate and exact cellular decompositions.
Abstract: This paper surveys recent results in coverage path planning, a new path planning approach that determines a path for a robot to pass over all points in its free space. Unlike conventional point-to-point path planning, coverage path planning enables applications such as robotic de-mining, snow removal, lawn mowing, car-body painting, machine milling, etc. This paper will focus on coverage path planning algorithms for mobile robots constrained to operate in the plane. These algorithms can be classified as either heuristic or complete. It is our conjecture that most complete algorithms use an exact cellular decomposition, either explicitly or implicitly, to achieve coverage. Therefore, this paper organizes the coverage algorithms into four categories: heuristic, approximate, partial-approximate and exact cellular decompositions. The final section describes some provably complete multi-robot coverage algorithms.
1,206 citations
"A framework for area coverage and t..." refers background in this paper
...At this point in our development, the waypoints are arranged in the mission environment to allow the robot to comb the area in a basic "lawn mowing" fashion much like the simple back-and-forth motions described in [ 22 ]....
[...]
...Area coverage or coverage path planning is essentially the generation of a path that results in a robot travelling to all "free" or unoccupied points in an area [ 22 ] and has been identified as being highly applicable to search and rescue [23]....
[...]
01 May 2004
TL;DR: The article presents a synopsis of the major HRI issues in reducing the number of humans it takes to control a robot, maintaining performance with geographically distributed teams with intermittent communications, and encouraging acceptance within the existing social structure.
Abstract: Rescue robotics has been suggested by a recent DARPA/NSF study as an application domain for the research in human-robot integration (HRI). This paper provides a short tutorial on how robots are currently used in urban search and rescue (USAR) and discusses the HRI issues encountered over the past eight years. A domain theory of the search activity is formulated. The domain theory consists of two parts: 1) a workflow model identifying the major tasks, actions, and roles in robot-assisted search (e.g., a workflow model) and 2) a general information flow model of how data from the robot is fused by various team members into information and knowledge. The information flow model also captures the types of situation awareness needed by each agent in the rescue robot system. The article presents a synopsis of the major HRI issues in reducing the number of humans it takes to control a robot, maintaining performance with geographically distributed teams with intermittent communications, and encouraging acceptance within the existing social structure.
593 citations
"A framework for area coverage and t..." refers background in this paper
...examine narrow voids in rubble that is too unstable for humans and rescue dogs to enter [5,6,7,4,8]....
[...]
...Furthermore, decreased cognitive workload levels translate to better awareness of the robot's situation, enhancing the supervisor's abilities for good decision making [6] as well as for diagnosing and handling robot anomalies or failures [20,21]....
[...]
...Notably, robots have in fact been deployed at ground zero in New York after the September 11 attacks [6] as well as in the aftermath of Hurricane Katrina in 2005 [9] to help search for victims....
[...]
Book•
01 Jan 1995TL;DR: As you have no d oub t noticed , the authors are trying som ething a little d if ferent a t this year’s m eeting; they have invited several groups to share their experiences in developing and using com puter supprt sys tems to give some background in form ation on why they’re doing this and what they hope to achieve.
Abstract: As you have no d oub t noticed , we are trying som ething a little d if ferent a t this year’s m eeting; we have invited several groups to share w ith us the ir experiences in developing and using com puter supprt sys tems. My purpose here this m orn ing is to give you some background in form ation on why we’re doing this and w hat we hope to achieve. I t’s a surprise to no one th a t com puter technology has been a d vancing at a fan tastic ra te over the past few years. W hat does surprise m e, at least, is th a t it shows no signs of slowing down. I t ’s h a rd enough to keep track of the advances being m ade each week, let alone trying to figure ou t w hat to actually buy!!! I t ’s only too bad th a t o ther areas w ithin our technological society have not m ade sim ilar advances. I recently read a paper by a no ted h istorian th a t suggested th a t if technology and productiv ity in o ther industries had progresses at the sam e ra te as com pu te r technology, a flight around the world would take only 24 m inutes and Cadillacs w ould get 600 miles per gallon!!! W hile such analogies m ay be true on the surface, they d o n ’t tell the whole story. For exam ple, if we were to focus on o ther characteristics of this rapid ly grow ing technology, we would find th a t ou r $600 C adillac could only be driven by certain individuals, could only use one type of gas; would have users m anual th a t only a few people could read or understand , and it would be extrem ely difficult to get anyone to ride w ith you! At the sam e tim e our analytical capabilities are increasing expon entially, costs are decreasing at a sim ilar ra te . Tw enty five years ago it cost about $1.25 to perform 100,000 m ultip lications using a digital com puter. T oday, such a task costs m uch less th a n a penny. I t ’s possible for an individual to ren t tim e on an in te rna tiona l com m unications n e t work and send in form ation v irtually anyw here in the world at the ra te of 40 m illion bits per second. This is roughly equal to 480,000 university professors ta lk ing at the sam e tim e. These trem endous technological advances are not w ithout p o ten tially serios side effects, however. T h e n a tu re and severity of these p ro blems depend on w here you stand . From my position, for exam ple, a m ajo r p rob lem w ith com puters is tha t they are getting so affordable, and so easy to use, tha t it is ge tting very d ifficult to im press people with
381 citations
TL;DR: An overview of the use of robots for USAR is provided, concentrating on what robots were actually used and why, and the roles that the robots played in the response and the impact of the physical environment on the platforms.
Abstract: On September 11, 2001, the Center for Robot-Assisted Search and Rescue (CRASAR) responded within six hours to the World Trade Center (WTC) disaster; this is the first known use of robots for urban search and rescue (USAR). The University of South Florida (USF) was one of the four robot teams, and the only academic institution represented. The USF team participated onsite in the search efforts from 12-21 September 2001, collecting and archiving data on the use of all robots, in addition to actively fielding robots. This article provides an overview of the use of robots for USAR, concentrating on what robots were actually used and why. It describes the roles that the robots played in the response and the impact of the physical environment on the platforms. The quantitative and qualitative performance of the robots are summarized in terms of their components (mobility, sensors, control, communications, and power) and within the larger human-robot system. Lessons learned are offered and a synopsis of the current state of rescue robotics and activities at the CRASAR concludes the article.
280 citations
"A framework for area coverage and t..." refers background in this paper
...examine narrow voids in rubble that is too unstable for humans and rescue dogs to enter [5,6,7,4,8]....
[...]