Search

Effective path planning is crucial for mobile robots to quickly reach rescue destination and complete rescue tasks in a post-disaster scenario. In this study, we investigated the post-disaster rescue path planning problem and modeled this problem as a variant of the travel salesman problem (TSP) with life-strength constraints. To address this problem, we proposed an improved iterated greedy (IIG) algorithm. First, a push-forward insertion heuristic (PFIH) strategy was employed to generate a high-quality initial solution. Second, a greedy-based insertion strategy was designed and used in the destruction-construction stage to increase the algorithm's exploration ability. Furthermore, three problem-specific swap operators were developed to improve the algorithm's exploitation ability. Additionally, an improved simulated annealing (SA) strategy was used as an acceptance criterion to effectively prevent the algorithm from falling into local optima. To verify the effectiveness of the proposed algorithm, the Solomon dataset was extended to generate 27 instances for simulation. Finally, the proposed IIG was compared with five state-of-the-art algorithms. The parameter analysis was conducted using the design of experiments (DOE) Taguchi method, and the effectiveness analysis of each component has been verified one by one. Simulation results indicate that IIG outperforms the compared algorithms in terms of the number of rescue survivors and convergence speed, proving the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

In order to enable rescue robots to accurately detect human joint points in dangerous building environments to replace rescuers into dangerous scenes. A machine learning based human joint point detection method was proposed. Firstly, human joint detection data was obtained through Kinect cameras, and normalized methods were used to smooth and preprocess the joint data. Secondly, human joint length constraints and joint rotation angle constraints were added to the preprocessed data to generate the spatial positions of each human joint point. Finally, the Tsai method was used for hand eye calibration to obtain the distance between the robotic arm and the injured person. The experimental results show that the method accurately measures the position of the casualty joint point in the rescue environment of a dangerous building, which verifies the effectiveness of the proposed detection method. [ABSTRACT FROM AUTHOR]

Natural calamities are affecting many parts of the world. Natural disasters, terrorist attacks, earthquakes, wildfires, floods and all unpredicted phenomena. Disasters cause emergency conditions, so imperative to coordinate the prompt delivery of essential services to the sufferers. Often, disasters lead many people to perish by becoming trapped inside, but many more also perish as a result of individuals receiving rescue either too late or not at all. The implementation and design of a Receiver module utilizing Davinci code processor DVM6437, Wireless camera receiver, Zigbee Transceiver and Global Positioning System (GPS) is proposed in this manuscript for Wireless Vision-based Semi-Autonomous rescue robots that are employed in rough terrain. The receiver side's Zigbee transceiver module eliminates the limitations of tele-operating rescue robots by enabling the control station to receive GPS data signals and aids in robot management by sending control signals wirelessly. Half and full-duplex communication are supported by the Davinci processor DVM6437, a digital media fixed-point DSP processor that relies on Very Long Instruction Words. It includes an extensive instruction set that is ideal for real-time salvage operations. DVM processor is coded utilizing MATLAB Simulink. MATLAB codes and Simulink blocks are employed under Embedded IDE link. [ABSTRACT FROM AUTHOR]

This paper mainly discusses the development status, pain points and future trend of China’s coal mine robot industry. In the context of the “robot +” era, this paper expounds the development of China’s robot industry from the aspects of the number of robot enterprises, regional distribution, industrial park construction, advantage track, national policy, etc., and expounds the changes and challenges brought by the domestic Internet and manufacturing enterprises. This paper focuses on the analysis of coal mine robot technology and industry pain points, and extracts three major capabilities that coal mine robot should have to realize intelligence. Strengthening the construction of supply chain and standard system is proposed. The classification standard of coal mine robot L0-L5 is introduced in detail.

Tracked robots equipped with flippers and LiDAR sensors have been widely used in urban search and rescue. Achieving autonomous flipper control is important in enhancing the intelligent operation of tracked robots within complex urban rescuing environments. While existing methods mainly rely on the heavy work of manual modeling, this paper proposes a novel Deep Reinforcement Learning (DRL) approach named ICM-D3QN for autonomous flipper control in complex urban rescuing terrains. Specifically, ICM-D3QN comprises three modules: a feature extraction and fusion module for extracting and integrating robot and environment state features, a curiosity module for enhancing the efficiency of flipper action exploration, and a deep Q-Learning control module for learning robot-control policy. In addition, a specific reward function is designed, considering both safety and passing smoothness. Furthermore, simulation environments are constructed using the Pymunk and Gazebo physics engine for training and testing. The learned policy is then directly transferred to our self-designed tracked robot in a real-world environment for quantitative analysis. The consistently high performance of the proposed approach validates its superiority over hand-crafted control models and state-of-the-art DRL strategies for crossing complex terrains. [ABSTRACT FROM AUTHOR]

This paper proposes a novel design strategy and task‐priority‐based control methodology for a robot to successfully complete a rescue operation in an extremely unstructured environment. The mechanical structure is designed to obtain both versatile manipulability and all‐terrain mobility. The regularized hierarchical quadratic program is used for whole‐body motion and force control. The optimization strategy is reasoning about regularization and thus it ensures convergence of the solution in the face of singularities while taking into account equality and inequality constraints. We demonstrate the effectiveness of the online optimization‐based control algorithms through extensive real‐world numerical and experimental results. Finally, we highlight that the rescue robot can successfully execute missions to extract a casualty and dispose of a dangerous object both indoor and outdoor environments. [ABSTRACT FROM AUTHOR]

The underground building environment plays an increasingly important role in the construction of modern cities. To deal with possible fires, collapses, and so on, in underground building space, it is a general trend to use rescue robots to replace humans. This paper proposes a dual‐robot system solution for search and rescue in an underground building environment. To speed up rescue and search, the two robots focus on different tasks. However, the environmental perception information and location of them are shared. The primary robot is used to quickly explore the environment in a wide range, identify objects, cross difficult obstacles, and so on. The secondary robot is responsible for grabbing, carrying items, clearing obstacles, and so on. In response to the difficulty of rescue caused by unknown scenes, the Lidar, inertial measurement unit and multiview cameras are integrated for large‐scale 3D environment mapping. The depth camera detects the objects to be rescued and locate them on the map. A six‐degree‐of‐freedom manipulator with a two‐finger gripper is equipped to open doors and clear roadblocks during the rescue. To solve the problem of severe signal attenuation caused by reinforced concrete walls, corners and long‐distance transmission, a wireless multinode networking solution is adopted. In the case of a weak wireless signal, the primary robot uses autonomous exploration for environmental perception. Experimental results show the robots' system has high reliability in over‐the‐horizon maneuvering, teleoperation of the door opening and grasping, object searching, and environmental perception, and can be well applied to underground search and rescue. [ABSTRACT FROM AUTHOR]

In this study, we develop a novel damper prototype for robot manipulators of a mobile robot to perform rescue operations in extreme environments like battlefields. Shock vibrations occur when such robots drive over rugged terrain, adversely affecting both the robot and the rescued person. We propose a joint module that utilizes magnetorheological (MR) fluid to depress environmental impact vibrations. To do this, we first suggest a novel structure for our MR damper, with multiple working coils to augment the magnetic field intensity for the given volume; then, we perform dynamic simulations on the manipulator with the suggested MR damper installed, examining vertical impact acceleration and the driving torque generated in the joint module. The proposed damper can best reduce the amplitude of vibrations by about 90 % at 21 Hz and by about 30 % at the system's resonant frequency of 22 Hz, which are the frequencies of interest as those lie around the natural frequency of the robot arm. [ABSTRACT FROM AUTHOR]

Tracked robots equipped with flippers and LiDAR sensors have been widely used in urban search and rescue. Achieving autonomous flipper control is important in enhancing the intelligent operation of tracked robots within complex urban rescuing environments. While existing methods mainly rely on the heavy work of manual modeling, this paper proposes a novel Deep Reinforcement Learning (DRL) approach named ICM-D3QN for autonomous flipper control in complex urban rescuing terrains. Specifically, ICM-D3QN comprises three modules: a feature extraction and fusion module for extracting and integrating robot and environment state features, a curiosity module for enhancing the efficiency of flipper action exploration, and a deep Q-Learning control module for learning robot-control policy. In addition, a specific reward function is designed, considering both safety and passing smoothness. Furthermore, simulation environments are constructed using the Pymunk and Gazebo physics engine for training and testing. The learned policy is then directly transferred to our self-designed tracked robot in a real-world environment for quantitative analysis. The consistently high performance of the proposed approach validates its superiority over hand-crafted control models and state-of-the-art DRL strategies for crossing complex terrains.

Due to the perilous conditions in coal mine accidents, trapped people need to be rescued as soon as possible. The danger and complexity of this environment have brought great difficulties for search and rescue. The emergence of rescue robots has addressed this problem, and the improvement of their search-and-rescue ability is a key concern for rescue robot designers. Based on previous experience of a tracked mobile robot, this paper proposes a new solution via the addition of adjustive rocker arms. For this purpose, a hydraulic unit is installed between the rocker arms and the robot, which enables the rocker arms to be pulled back and forth, enabling its adaptation to more complex environments. In addition, based on kinematics equations, by analyzing the motion rules and characteristics of climbing typical obstacles including stairs, grooves, and lug steps, the present research not only works out the centroid coordinates but also explores the maximal obstacle height. The results show that when the rocker arms are extended by hydraulic pressure, the obstacle-climbing height of the robot increases 16.7 percent. This demonstrates the improvement in obstacle climbing ability and rescue efficiency in complex environments. [ABSTRACT FROM AUTHOR]

Copyright of Chinese Medical Equipment Journal is the property of Chinese Medical Equipment Journal Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

A kind of coal mine rescue robot with planetary wheel as movement mechanism and 5G technology as communication system is designed. The vertical obstacle-surmounting ability of coal mine rescue robot in unknown environment can be improved by using the high-power transmission characteristic of compact planetary gear structure. By using 5G network, the signals such as video, voice, the position of trapped miners and obstacles can be quickly transmitted, which is helpful for rescuers to know the underground situation in time and to work out a scientific rescue plan, which can improve the rescue efficiency and success rate.

Copyright of Chinese Medical Equipment Journal is the property of Chinese Medical Equipment Journal Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this paper, we propose a semantic simultaneous localization and mapping (SLAM) framework for rescue robots, and report its use in navigation tasks. Our framework can generate not only geometric maps in the form of dense point-clouds but also corresponding point-wise semantic labels generated by a semantic segmentation convolutional neural network (CNN). The semantic segmentation CNN is trained using our RGB-D dataset of the RoboCup Rescue-Robot-League (RRL) competition environment. With the help of semantic information, the rescue robot can identify different types of terrains in a complex environment, so as to avoid specific obstacles or to choose routes with better traversability. To reduce the segmentation noise, our approach utilizes depth images to perform filtering on the segmentation results of each frame. The overall semantic map is then further improved in the point-cloud voxels. By accumulating results of multiple frames in the voxels, semantic maps with consistent semantic labels are obtained. To show the advantage of having a semantic map of the environment, we report a case study of how the semantic map can be utilized in a navigation task to reduce the arrival time while ensuring safety. The experimental result shows that our semantic SLAM framework is capable of generating a dense semantic map for the complex RRL competition environment, with which the arrival time of the navigation time is effectively reduced.

The goal of this article is to find an optimal and robust solution for on-line hierarchical least-squares optimization subject to both equality and inequality constraints. We focus on the reasoning about the task regularization to ensure the convergence and robustness of a solution in the face a singularity. The mixed problem of a regularization and inequality-constrained hierarchical optimization is not fully discussed due to the mathematical complexity. We address this problem by formulating a regularized hierarchical quadratic programming. The solution is obtained in a unified and computationally efficient manner by leveraging a singular value decomposition and an active set method. At the same time, we concentrate on the realization of the proposed algorithm as a practical means of real-time whole-body motion generation. The effectiveness of the algorithm is validated through extensive numerical simulations and experimental tests of a rescue robot successfully executing manipulation missions in a highly unstructured environment. [ABSTRACT FROM AUTHOR]

Due to the perilous conditions in coal mine accidents, trapped people need to be rescued as soon as possible. The danger and complexity of this environment have brought great difficulties for search and rescue. The emergence of rescue robots has addressed this problem, and the improvement of their search-and-rescue ability is a key concern for rescue robot designers. Based on previous experience of a tracked mobile robot, this paper proposes a new solution via the addition of adjustive rocker arms. For this purpose, a hydraulic unit is installed between the rocker arms and the robot, which enables the rocker arms to be pulled back and forth, enabling its adaptation to more complex environments. In addition, based on kinematics equations, by analyzing the motion rules and characteristics of climbing typical obstacles including stairs, grooves, and lug steps, the present research not only works out the centroid coordinates but also explores the maximal obstacle height. The results show that when the rocker arms are extended by hydraulic pressure, the obstacle-climbing height of the robot increases 16.7 percent. This demonstrates the improvement in obstacle climbing ability and rescue efficiency in complex environments.

This paper considers the issue of the search and rescue operation of humans after natural or man-made disasters. This problem arises after several calamities, such as earthquakes, hurricanes, and explosions. It usually takes hours to locate the survivors in the debris. In most cases, it is dangerous for the rescue workers to visit and explore the whole area by themselves. Hence, there is a need for speeding up the whole process of locating survivors accurately and with less damage to human life. To tackle this challenge, we present a scalable solution. We plan to introduce the usage of robots for the initial exploration of the calamity site. The robots will explore the site and identify the location of human survivors by examining the video feed (with audio) captured by them. They will then stream the detected location of the survivor to a centralized cloud server. It will also monitor the associated air quality of the selected area to determine whether it is safe for rescue workers to enter the region or not. The human detection model for images that we have used has a mAP (mean average precision) of 70.2%. The proposed approach uses a speech detection technique which has an F1 score of 0.9186 and the overall accuracy of the architecture is 95.83%. To improve the detection accuracy, we have combined audio detection and image detection techniques.

For individuals trapped in a fire, early detection can significantly increase their chances of survival. Presently, firefighters employ a systematic search method along the walls, ensuring a comprehensive and thorough exploration of the environment to prevent missing any trapped victims. However, this approach has its drawbacks, such as time wastage in areas or rooms without victims. The goal of this study is to propose a search method that can expedite the discovery of trapped victims. Our method relies primarily on prior knowledge, crowd information and the temperature within the fire scene, utilizing fuzzy logic to calculate the probability of the presence and survival of victims in each distinct space. The resulting search sequence not only accelerates victim discovery but also safeguards firefighters from unnecessary risks. We conducted various simulation experiments to validate our approach. In comparison to the sequential search method currently employed by firefighters, the experimental results indicate that our method reduces the time to locate trapped victims by 25 %. Compared to other path planning algorithms based on approximate optimization, our method offers a shorter computation time, making it suitable for integration into fire rescue systems to provide real-time assistance. [ABSTRACT FROM AUTHOR]

Based on analysis of principle and characteristics of traditional water inrush source, fire and gas concentration detection technologies of coal mine rescue robot, water inrush source detection method of coal mine rescue robot based on wireless ad-hoc network, fire detection method of coal mine rescue robot based on big data and gas concentration detection method of coal mine rescue robot based on multi-source information fusion were proposed, which could effectively improve accuracy of water inrush water, fire and gas concentration detection of coal mine rescue robot. It was pointed out that disaster environment detection technology of coal mine rescue robot would deeply integrate modern information technologies such as cloud computing, artificial intelligence and Internet of things, so as to comprehensively improve reliability of disaster environment detection results of coal mine rescue robot.

Disaster robots are needed to perform various tasks through narrow gaps between building debris to be used for rescue. A soft material-based disaster robot can have easy access to the rescue site through the narrow gaps. To ensure the robust control and better performance of the soft robot operation, a joint stiffness modulation mechanism is required. In this paper, we have proposed a noble stiffness modulation mechanism that includes shape change and self-assembly by using a particle flow-based inflatable robot body. We analyzed the particle filling completion time by injecting air and particles at a constant pressure into the soft chamber depending on several parameters (the size of the particle, the size of the reservoir, the volume ratio between the chamber volume and the total volume of the particle, and the injected air pressure). Of these, the most dominant factors influencing the completion time were particle size and pressure. It was observed that the smaller the size of the particle, the shorter time. The completion time tended to decrease as the air pressure increased. [ABSTRACT FROM AUTHOR]

In the 4th industrial revolution era, more countries and companies tend to use specialized robots to replace workers. Especially in a hazardous and high risks working environment, robots that perform human tasks are also humanistic. It's even the unique solution to ensure life safety. Currently, scientists are much interested in robots that look, act like animals; including biomimetic robot models have capable of flexible mobility and widely application potential. However, it's difficult to calculate, design and manufacture dynamic robots. In this article, the author will present an overview of dynamic robots and propose new methods and calculation techniques to design and build biomimetic robots. The experimental results show that proposals have contributed to solve those difficulties and being practically applicable to make a biomimetic robot. [ABSTRACT FROM AUTHOR]

Copyright of Chinese Medical Equipment Journal is the property of Chinese Medical Equipment Journal Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this research, we aim to develop a method to recognize three dimensional shape of stacked rubbles each by each for rubble withdrawal rescue robots. Shapes, masses, states of stacked rubbles and so on are various and unknown at disaster areas. Then, grasping positions on rubbles and ways to remove them have to be considered for not breaking down the stacked rubbles and falling them down on victims. Thus, it is necessary to recognize stacked rubble individually and to identify their features, such as shapes, masses, center of gravity positions and so on. In this paper, we propose a 3-D object shape recognition system with a RGB-D sensor and a 3-D reference marker. Moreover, we also propose an extraction method of rubbles using the SSD (Single Shot Multi Box Detector) of the AI (Artificial Intelligence). Experiments were performed to confirm the validity of the proposed method with our constructed prototype of a rescue robot. Through the experiments, it is shown that target stacked rubbles were recognized individually. [ABSTRACT FROM AUTHOR]

This paper describes the development of three‐dimensional (3D) human recognition system of flying drone system for emergency rescue and investigation. In this system, deep neural network and its application for 3D object recognition are key techniques for human detection from a free viewpoint. Some appearance based characteristics are captured as movie frames, and the system uses deep neural networks to automatically classify concerned object. The proposed system performs well that many kinds of views of personnel can be recognized from bird's eye view. Experimental results show that the system can effectively recognize human objects with high accuracy. [ABSTRACT FROM AUTHOR]

For limitation of the maximum permitted size and weight, a mine rescue robot(MRR) swing arm driving system was designed by taking a form of single-inverter driving dual-motor. The system model was built by use of weighted sum method, and current relationship of the dual-motor of the model was deduced and analyzed. For inconsistent MRR swing arm loads caused by complicated working conditions in coal mine underground, a balance control method for the system was proposed based on active damping mechanism. The method was tested by use of a 15 kW MRR prototype, and the result shows that the method can realize dynamic matching of torque under condition of inconsistent MRR swing arm loads.

Development background of coal mine rescue robot was introduced, and research status and application situation of coal mine rescue robot at home and abroad were summarized. Some technical problems about robots taking part in coal mine rescue work were analyzed and pointed out, such as poor terrain adaptability, large size, short effective working distance, defective intelligence, low stability and so on. Technical development direction of coal mine rescue robot was put forward, namely bionic mechanical structure, efficient energy, lightweight materials, intelligent machine control, collaborative rescue and modular design. It was also pointed out that the future development of coal mine rescue robot would be accompanied with common development of various technologies.

In order to solve path planning problem of coal exploration and rescue robots in three-dimentional environment, an optimal path planning method for coal exploration and rescue robot based on improved ant colony algorithm was proposed. Three-dimensional space environment model is established by using grid method, and path planning objective function of coal exploration and rescue robot is established. Node transition probability design, node selection strategy and pheromone update strategy are optimized and improved by introducing new heuristic function factor, random selection mechanism of node and combining strategy of local updating and global updating. Matlab simulation results show that both the traditional ant colony algorithm and the improved ant colony algorithm can find an optimal path for the coal exploration and rescue robot in the three-dimensional environment model. Under different task requirements, the improved ant colony algorithm can effectively shorten the length of search path and reduce time of path search, and has strong decision-making ability and good convergence performance.

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Chinese Medical Equipment Journal is the property of Chinese Medical Equipment Journal Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Coal Science & Technology (0253-2336) is the property of Coal Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

After the occurrence of a disaster, it is critical to perform rapid and accurate searching operations in the large disaster area. It is efficient to perform such operations using multiple mobile exploration robots. Accordingly, we focus on cooperative cruising in a disaster environment and propose the trajectory tracking control method for a semi-autonomous search robot. We apply a robot operating system (ROS) to execute the trajectory tracking control using two mobile exploration robots. In this paper, we describe the trajectory tracking control using gravity potential method and the results of a cooperative cruising experiment in an uneven terrain environment. [ABSTRACT FROM AUTHOR]