Search

The humanoid robot is to give an innovative concept to handle the bore well rescue operations. Due to drought and depletion of underground water more bore wells are drilled on the surface of the earth. When the ground water gets dried or polluted, the motor along with casing pipe are removed and the outer, surface of the bore is not insulated properly. As a result of this, the children who were playing near the bore, accidently fall into it which has drunk their lives. A small delay in the rescue can cost the child his or her life. To lift the child out the narrow confines of the bore wells is also not very easy. The rescue process to save the child from bore well is a long and complicated process. The rescue team tries to approach the victim from a parallel well that take about 20–60 h to dig. This complicated process makes 70% of the rescue operations fail. This brings out safety that how far the robot handles the child safely. Thus we propose an idea where a human-like hand using the Inverse kinematic technique is implemented ,here the damage caused is drastically reduced and by using a wireless technology which we can use without the fear of damaging the wire after being sent into the pit .We have also placed an wireless camera and a LED which will relay the information to the device and the LED is for the light requirement inside the pit. We have also placed a path provide oxygen supply to the child through filter. We have also increased the number of DOF (Degree Of Freedom)by three linear movements[3L].These components can be slightly altered and used for almost all rescue operation fully or partially by the robot.

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.

One of the most challenging and non-trivial tasks in robotics-based rescue operations is Hazardous Materials or HAZMATs sign detection within the operation field, in order to prevent other unexpected disasters. Each Hazmat sign has a specific meaning that the rescue robot should detect and interpret it to take a safe action, accordingly. Accurate Hazmat detection and real-time processing are the two most important factors in such robotics applications. Furthermore, we also have to cope with some secondary challengers such as image distortion problems and restricted CPU and computational resources which are embedded in a rescue robot. In this paper, we propose a CNN-Based pipeline called DeepHAZMAT for detecting and segmenting Hazmats in four steps; 1) optimising the number of input images that are fed into the CNN network, 2) using the YOLOv3-tiny structure to collect the required visual information from the hazardous areas, 3) Hazmat sign segmentation and separation from the background using GrabCut technique, and 4) post-processing the result with morphological operators and convex hall algorithm. In spite of the utilisation of a very limited memory and CPU resources, the experimental results show the proposed method has successfully maintained a better performance in terms of detection-speed and detection-accuracy, compared with the state-of-the-art methods.

A novel transformable wheel-legged robot, namely Land Devil Ray (LDR), is proposed for search and rescue mission in complex terrains. Inspired from spatial folding mechanism and metamorphic mechanism, a multi-four-bar linkage transformable wheel-legged locomotion mechanism is proposed for LDR, which can transform from circle-wheeled mobility to wheel-legged mobility, or vice versa, for adaptability of different terrains. Aimed to minimize the robot actuators, the wheel-legged transformation is designed to be triggered passively when contacting the obstacles, or be actively driven without extra actuator by active triggering mechanism. The parameters of wheel-legged structure are optimized as well for an optimal transformation success rate and better obstacle-negotiation capability. A prototype of LDR robot is conducted, and its experiment results show that the proposed robot integrates the advantages of both wheeled and legged mobility, and has excellent performance in maneuverability, stability, maximum obstacle-negotiation height and mode switch process, such as transformation ratio as 1.88, transformation success rate as 100%, and ability to over obstacles 2.8 times as tall as its wheel radius. Lessons learned from the proposed robotic mobility and its results have general applicability to search / rescue robots, and other types of mobile robots as well.

Performing search and rescue tasks in the ruins after disasters demand rescue robots with slender and compliant structure to accommodate the complicated configurations under debris. This paper presents the structural design and system composition of a novel tendon-sheath actuated compliant rescue manipulator with slender and flexible body. The proposed robot can drill into the narrow space where rescuers and traditional rigid robots cannot get in because of size limitation or toxic environment. The self-sensing calibration, dynamic modeling, and hybrid force/position control trajectory of the compliant gripper with integrated position and force monitoring capabilities are analyzed and discussed. With the aim of regulating the gripper displacement and clamping force during operation, a hybrid force/position control strategy is proposed based on a cascaded proportional-integral-derivative (PID) controller and a fuzzy sliding mode controller (FSMC). Experimental setups mainly consisting of servo motor, tendon sheath transmission components, compliant gripper, and real-time control system are established to calibrate the strain gauge sensors and identify the dynamic model parameters. Further experimental investigations involving force tracking experiments, position tracking experiments, and object grasping experiments are carried out. The experimental results demonstrate the effectiveness of the developed self-sensing approach and control strategies during rescue operation.

Modern public services are nowadays capable of conducting complex operations in case of various natural or man-made hazards. In last decades, the responsibilities of the fire services have been significantly extended from ‘ordinary’ fire-fighting to complex operations including technical rescue, but also chemical, biological, radiological, nuclear rescue. Therefore this crucial public service is being constantly equipped with the newest and the most efficient solutions aiming at optimization of their primary activity, which saves victims lives. Thanks to INSARAG guidelines, activities of certified heavy urban search and rescue groups (HUSAR) are based on solid foundations: knowledge and experience gained during historical events in last decades. However, rapid technological progress might be beneficial. The article describes the MOBNET system, that is currently under development. There was a research work conducted to gather end-user requirements in purpose to create a tailor-made solution supporting traditional activities of USAR teams. The target group of the system has been extended, as other public services might benefit from the system implementation as well. The system will use combined DCT – EGNSS technology to track victims.

An extended nonlinear Kalman filter (EKF) for a real-time estimation of the navigation parameters of autonomous underwater vehicles (AUVs) based on the combination of angular rate sensors, magnetometers, accelerometers and speedometers, pressure sensors or GPS is recently developed. Due to the combination of the measuring devices using the EKF, the accuracy of the navigation parameters is improved because the drifts of angular rate sensors, accelerometers and noise of the measuring devices are ignored. Moreover, this combination helps us to reduce the capacity of the computation in comparison with the inertial navigation methods. We combine the inertial navigation equipments with the speed measurement devices based on an extended Kalman filter in order to improve the speed accuracy of an underwater equipment. The obtained results of the test on the turntable with 3 degrees of freedom Aerosmith and of the firm test on underwaterr rescue robots for big fire have proved the correctness of the algorithm.

Robots for rescue operations after a disaster are an interesting and challenging research problem that has the potential to save lives and reduce economic losses after a disaster. We developed TOPTWR, an extension of the popular TOPTW model, to model the issues in task allocation for teams of rescue robots. Our hybrid algorithm is based on a team of heterogeneous humanoid robots trying to optimize five objectives (task rewards, task completion time, total energy, maximum energy consumption for a single robot, and missed deadline penalties). A common approach to solve these kinds of problems are multi-objective evolutionary algorithms (MOEAs), but their major disadvantage is that they cannot deal with dynamic environments easily. This paper presents an efficient solution for TOPTWR by combining MOEAs with learning algorithms. A novel Extended Multi-Start Simulated Annealing Iterated Local Search (EMSAILS) operator using a modern state-of-the-art NSGA-III algorithm is proposed. In addition, we applied Q-Learning to learn the likely changes in the environment and how to react to them. This algorithm, HMO-TOPTWR-NSGA-III (HMO-N-L), uses an artificial neural network (ANN) as a function approximator to make the huge state and action spaces tractable. This paper includes a thorough empirical evaluation demonstrating the effectiveness of the multi-objective algorithm in both static and dynamic environments. The evaluation shows that the proposed algorithm reduces the error by up to 42% against three state-of-the-art approaches to TOPTW (HMO-N, MSA, and IPI).

Thermal control is one of the most crucial problems for electronic devices on nuclear emergency rescue robot due to the harsh operating conditions. Phase change material (PCM) based heat sink and heat insulation layers, serving as a passive thermal control system, were applied for motor driver as a case for electronics protection on nuclear rescue robot. Two types of PCM based thermal control systems for both room temperature and elevated temperature environments were proposed considering the nuclear accident condition. The anti-irradiation property of an organic commercial PCM OP44E was studied. Experiments were conducted to investigate effects of system structure and heat source power on the temperature control. Results showed that the system can greatly prolong the motor driver's safe running time for more than 1 hour without any power consumption. The best working time was almost linearly decreased with the increase of the input power. High temperature test at 100 °C indicated that the motor driver could safely operate for more than 98 min. The PCM based support frame increased 54% of the best working time.

Compared with series mechanisms, a parallel mechanism has the merits of high stiffness, fast response, and centralised layout of electric cylinders, which is more suitable for the mechanical leg of a rescue robot. However, it is not flexible enough to improve the environment adaptability of the robot. Adding the abilities of reconfiguration and mobility change to general parallel mechanisms, a novel metamorphic parallel mechanism for robotic legs is proposed based on an innovative rotatable-axis revolute joint. The inverse kinematic model of the new mechanism is established and the constraint conditions and ranges of the key parameters are explored, as well as obtaining the cloud picture of its workspace. The stiffness model is formulated with the consideration of the deformation of the main components caused by the actuation and constraints, utilising the screw theory. The stiffness matrices of the home positions of configurations I and III are then acquired and the stiffness distributions in the sub-workspace around the desired trajectory are evaluated, which are expected to lay a good theoretical foundation for the application of this novel mechanism.

Rescue robotics is a domain with great potential for important, real-life applications. Recently its development mostly focused on creating machines able of moving in collapsed buildings remains, leaving group operations in undamaged buildings slightly neglected. In this paper we are focusing on methods for managing multi-robot rescue actions in buildings, where some damages should be expected, but the general structure of a building remains unchanged. We propose a predictive planning approach, which allows using time demanding optimization algorithms for the task, where environment can change rapidly. The proposed solution predicts possible exceptional situations and pre-calculates alternative plans. A prototype system for parallel calculating of plans using high performance computing hardware is presented. A comparison of the optimized plans with a greedy approach is shown for different buildings and different sizes of robot teams. Finally the evaluation of the approach on real mobile robots is described.

Underground mining is beset with numerous problems such as ground movement (fall of roof/sides), inundation, air blast, etc.; apart from gas explosions and dust explosions that are restricted to coal mines. Whatever may be the cause and type of accident or the extent of damage caused, it is a horrendous task for the rescue team to reach the trapped miners. The accident/irrespirable zone contains increased levels of harmful gases like carbon dioxide and carbon monoxide and explosive gases like methane apart from a deficiency of Oxygen. The entire gallery or roadway is filled with dust and smoke, or water in case of inundation, hindering the visibility of rescue personnel. Thus, it is not an ideal situation for the rescue team to perform the operations. The first few hours after the disaster are the critical moments that could be the difference between life and death of the trapped miners. Hence, the ideal solution in such cases would be to deploy a wireless robot equipped with various gas sensors and cameras to aid visibility even in extremely low light conditions. This paper reviews some notable examples from the past and highlights important requirements for rescue robots along with some limitations encountered in the design of such robots.

In some cases, rescuing people in danger with the help of autonomous evacuation devices is the only way to save their lives. This is true, in particular, for oil platform accidents, which nowadays result in a lot of victims. This paper describes a way to solve this problem using a group of rescue robots. Taking into account the specific character of organizing rescue missions in extreme conditions, the article considers general principles of group formation and dividing the group into subgroups with different functions. Autonomy of individual robots and robot groups, redundancy of robots and interchangeability are considered as ways of increasing reliability. Some general approaches to solving the key problems of evacuation are also stated.

In most mobile robots, the ability to move from point to point in various types of terrain was the most crucial part to the design. Being able to survive through impact conditions is also essential for robots under hazardous circumstances such as rescue robots or military robots. In this paper, we designed and developed a robot with impact reduction mechanism which is based on the compliant design of its legs. The stiffness of the legs was designed to not only to serve walking purposes but also to help reduce the impact while dropping. An experiment was set to investigate how the radius of curvature of the connecting plate and the compliant leg of the robot play a role in impact absorption. The radius of curvature is one of the key factors which vary the stiffness of the compliant parts. With this design, the robot will gradually press the ground during landing using springlike legs. The compliant legs with nonlinear spring constant help absorb impact energy while the robot hits the ground. During drop-landing motion, the robot also transforms itself from a spherical shape into a legged robot while landing. The legs are extended into a walking mechanism on uneven terrain and retracted to create a ball shaped robot for rolling motion over smooth terrain. The transformation between the spherical shaped robot and the legged robot increase its motion capabilities under various conditions including falling, rolling and walking.

Mountain rescue is a new topic emerged after the expansion of emergency rescue function of public security fire force. This paper introduces the classification of mountain disaster incidents, analyzes mountain incidents rescue features. For Police Fire fighting Army which is the professional force and key contingent of emergency rescue, the measures of emergency rescue and the equipments used in mountain disaster incidents are presented, with the aim of offering reference for the implement of the most effective and best rescue measures in similar incidents in future.

The compact rescue robot (CRR), a quadruped pneumatically-actuated walking robot, seeks to use the benefits garnered from pneumatic power: force & power density, lightweight, inexpensive actuators, and inherent compliance. A simulation has been developed that models the dynamics of the robot and its interaction with the environment. However, development of an entirely new dynamic simulation specific to the system is not practical. Instead, the simulation combines a MATLAB/Simulink actuator simulation with a readily available C++ dynamics engine. The actuator simulation places particular emphasis on accuracy near the neutral position (the region most active during closed loop control), modeling this regime with a higher level of detail than observed in past literature. Because the multi-platform approach results in additional incurred challenges due to the transfer of data between the platforms, it is valuable to analyze the necessity of detail in the actuator model. The goal of this analysis is to find a balance of realistic behavior, model integrity, and practicality.

In this paper, a common model of task scheduling problems in agent rescue scenario is proposed, in which tasks with continuous dynamic damage are introduced to capture the emerging applications of using rescue robots and other resources to enhance human disaster rescue capability. Beyond this, we mainly focus on finding the optimal task scheduling strategy. We design a heuristic algorithm based on greedy strategy to obtain the optimal dynamic scheduling strategy of agents. Compared with solving global integer programming directly, the computational time is greatly reduced. The proof of the greedy strategy’s validity is also demonstrated under some specific damage functions. By comparing with the two strategies commonly used in real life, it is proved that our strategy is optimal. For practical application, we design an automatic negotiation framework, which realizes the real-time decentralized automated negotiation of agents. Then, using Game Description Language (GDL) as a tool, an automated negotiation algorithm is implemented, which enables agents to adjust the plan dispersedly. Experiments show that the algorithm is more efficient than the centralized algorithm in the case of limited communication.

Mine rescue robots play a vital role during rescues in underground mine disasters. In this paper, we propose a new navigation method by using diverse-sensor data fusion with an improved algorithm of the Neural Network Extended Kalman Filter. During this process, we take into account that a rescue’s effectiveness is limited by its single navigation model. First, we utilize the Back Propagation neural network to improve the data matching level of dissimilar sensors. Second, data fusion is carried out by combining the Extended Kalman Filter and the Back Propagation neural network. By doing so, we simultaneously retrain the Back Propagation neural network with the modified error signals. The experimental analysis showed that the algorithm can effectively deal with heterogeneous data fusion. It can also improve the convergent speed and time response of the algorithm, and further improve the accuracy of navigation.

To enhance the mobility of the rescue robot in amphibious environments, an eccentric paddle mechanism (ePaddle) has been proposed as the locomotion module for utilizing versatile locomotion gaits. In this paper, we focus on a unique legged race-walking gait among all the potential gaits of an ePaddle-based amphibious robot. This gait has advantages in stability and energy efficiency. We present kinematic-based methods for achieving race-walking by one ePaddle module. A planar path tracking method using race-walking gait is then proposed. Ideas of the race-walking gait as well as its planning methods are finally verified by simulations.

The centroid change equation, which is about six-track rescue robot with four swinging arms for mine emergency rescue, is solved by center of mass theory, the relationship between the centroid and angle of swing arms is derived. The graphs of the robot's centroid and the chart of the angle of the swing arms are drawn by calculation and Adams simulation, the results are agreement with each other. The rationality of the formula inference and the correctness of secondary development of Adams are verified. Then the plot of centroid changes is drown when rescue robot acrosses three steps, which provides the theoretical basis for the future study for controlling of robot's posture and the judgment of its stability when it crosses barriers.

A new type of mechanism has been designed to move an output point through a motion akin to a swimmer’s breast-stroke. The mechanism is designed to clear loose debris from around small mobile search and rescue robots. However, it has potential applications in many other domains that require controllable cyclic motion. This paper describes the mechanism concept and presents mathematical analysis of its design parameters. The properties of the mechanism were examined to understand how the mechanism trajectory can be altered mid-cycle whilst maintaining the condition of continually rotating motors. Furthermore, equations to calculate the mechanism torque ratio were derived. The analysis reveals limitations in the trajectory variations that can be implemented whilst maintaining the condition of continually rotating motors. The mechanism was manufactured to validate the mathematical predictions. It was found that the predicted torque ratios are within 90% of the experimentally obtained torque output. The mechanism was controlled using proportional-derivative control (PD) and demonstrated to track several desired trajectories without reversing the direction of motor travel, with tracking error less than ±4 mm.

Differential Evolution (DE) and Genetic Algorithms (GA) are population based search algorithms that come under the category of evolutionary optimization techniques. In the present study, these evolutionary methods have been utilized to conduct the optimum design of a fuzzy controller for mobile robot trajectory tracking. Comparison between their performances has also been conducted. In this paper, we will present a fuzzy controller to the problem of mobile robot path tracking for a CEDRA rescue robot. After designing the fuzzy tracking controller, the membership functions will be optimized by evolutionary algorithms in order to obtain more acceptable results.

Since mining accidents severely threaten production safety, robotic assistant systems can play an important role by searching and rescuing survivors in hostile underground environments. Accordingly, this paper focuses on the design, modeling and optimization of a 4UPS+PU spatial hybrid manipulator, which serves as the dexterous head section of a quadrupedal, groundhog-like mine rescue robot. This biologically inspired mechanism has three degrees of freedom (DOF), one translation and two rotations. Additionally, a passive leg is connected to both centers of the base and the moving platform in order to constrain undesirable motion. In order to evaluate the operational capacity, an analysis of the mobility and the inverse kinematics are conducted. The reachable workspace is generated with a boundary-searching discretization approach, and the local and global performance atlas, including stiffness and dexterity, are investigated. The multi-population evolution of structural and behavioral parameters is implemented to seek the optimal dexterity of the hybrid head mechanism.

After a coal mine disaster, especially a gas and coal dust explosion, the space-restricted and unstructured underground terrain and explosive gas require coal mine rescue robots with good obstacle-surmounting performance and explosion-proof capability. For this type of environment, we designed a mobile platform for a rocker-type coal mine rescue robot with four independent drive wheels. The composition and operational principles of the mobile platform are introduced, we discuss the flameproof design of the rocker assembly, as well as the operational principles and mechanical structure of the bevel gear differential and the main parameters are provided. Motion simulation of the differential function and condition of the robot running on virtual, uneven terrain is carried out with ADAMS. The simulation results show that the differential device can maintain the main body of the robot at an average angle between two rockers. The robot model has good operating performance. Experiments on terrain adaptability and surmounting obstacle performance of the robot prototype have been carried out. The results indicate that the prototype has good terrain adaptability and strong obstacle-surmounting performance.

Mobile robots are increasingly becoming an aid to humans in accomplishing dangerous tasks. Examples of such tasks include search and rescue missions, military missions, surveillance, scheduled operations (such as checking the reactor of a nuclear plant), and so forth. The advantage of using robots in such situations is that they accomplish high-risk task without exposing humans to danger: robots go where humans fear to tread. When dealing with robot teams for exploration missions, the human operator needs to control simultaneously multiple robots. This paradigm highly increases the difficulty of the operator task. In this paper, based on extensive experimental data, we are studying the problematic associated to the Single- Operator-Multiple-Robot Interaction. This analysis can help to ascertain the critical points in multi-robot control and supervision. The experiments have been done in a Search and Rescue scenario using USARSim.

This paper presents the wireless networking implementation of a dispersion and concentration movement algorithm for a team of search/rescue robots in an unknown environment. The goal of the dispersion movement is for the multi-robot team to spread out as widely as possible and explore any unknown targets without breaking the communication links among these robots. After one of the team members finding a target, other robots are commanded by the concentration movement to move to the same target location to, for example, retrieve the explored target or transport the target cooperatively. The only information used for designing the movement algorithms is the number of other robots within the communication range of the robot. The movement has its influence from the foraging behavior of the E. coli bacterium. The proposed algorithm is implemented on an 8051 microcontroller with an RF transceiver. The experimental results demonstrate the feasibility and convergence of the proposed algorithms in several typical scenarios.

When a natural disaster happens, it is very important to go to the place for rescue people as soon as possible. However, it is very hard to transport materials to rescue because the disasters destroy roads all over the area. Therefore, we can not use automobile. Moreover, the landform of the area must be so complex. In this paper, We propose a kind of walking robot system named CUL: Curry and Power Assist Robot for Unspecified Landform. To develop the system, we also propose a method for creating an environmental map. We call the method as "Mold Tube Method". And we describe a prototype of CUL which has two cameras and two legs. We show a plan of experiment for feasibility study.

It might be too late this time, but engineers around the world are working to prepare fleets of robots to help with the next mining disaster

I will introduce our research activities about robotic systems for rescue operation. I will discuss about snake-like robot suitable for the locomotion in a narrow and winding space and even in a dust-filled environment, and then demonstrates some of the examples; e.g. i) ACMR3, basic 3D snake like robots, ii)Soryu-III, three joints snake-like robot with crawlers, iii) Slime Slime robots, mechanisms with pneumatic actuators and bridle bellows, and iv) HELIXI, amphibious snake-like robot which makes specific spiral swimming motion just like spirochete. The effectiveness of the hyper-tether, robotic system utilizing tether traction mechanisms, will also shown. I will finally emphasize the effectiveness of ordinary-lifeembedded rescue devices, and demonstrate several examples such as a versatile jack-up device for automobiles.