Article
Chemistry, Multidisciplinary
Salvatore Rosario Bassolillo, Egidio D'Amato, Massimiliano Mattei, Immacolata Notaro
Summary: This paper proposes a distributed navigation strategy for a formation of UAVs in post-avalanche search-and-rescue operations. Formations offer more efficiency than single UAVs in dynamic and complex environments, distributing different sensors to reduce payload and increase robustness. The proposed approach was tested in two scenarios and successfully detected victims while maintaining situational awareness and avoiding unsearched areas.
APPLIED SCIENCES-BASEL
(2023)
Article
Environmental Studies
Robert Brown, David Molyneux, Joshua Ryan, Alexandria Major
Summary: Successful and early communication during maritime accidents is crucial for saving lives. Emergency radio beacons like EPIRBs and PLBs are reliable means for distress notification. However, Canada's regulations only require certain maritime activities to use these devices, leading to a higher fatality rate in other sectors. This paper discusses the governance structure for EPIRBs and PLBs in Canada, and proposes solutions to address challenges and gaps.
Article
Computer Science, Information Systems
Antonio Albanese, Vincenzo Sciancalepore, Xavier Costa-Perez
Summary: This paper presents SARDO, a drone-based search and rescue solution that leverages mobile phones to localize missing people. SARDO uses pseudo-trilateration and machine-learning techniques to rapidly determine the location of mobile phones with high accuracy and low battery consumption.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2022)
Article
Multidisciplinary Sciences
Gabriella Guelfi, Martina Iaboni, Anna Sansone, Camilla Capaccia, Michele Matteo Santoro, Silvana Diverio
Summary: Our research investigates the role of serum extracellular circulating miRNAs (ecmiRNAs) in dog stress response after search and rescue (SAR) of missing people. We found that let-7a and let-7f are differentially expressed after SAR and play a functional role in restoring cellular homeostasis through the p53 pathway.
SCIENTIFIC REPORTS
(2022)
Article
Geosciences, Multidisciplinary
Linjie Xing, Xiaoyan Fan, Yaxin Dong, Zenghui Xiong, Lin Xing, Yang Yang, Haicheng Bai, Chengjiang Zhou
Summary: This study proposes a multi-UAV cooperative system for wilderness search and rescue using target detection technology. By testing the system in simulated missions, it has been proven that the system can meet the requirements for search and rescue operations.
INTERNATIONAL JOURNAL OF DISASTER RISK REDUCTION
(2022)
Article
Computer Science, Interdisciplinary Applications
Ming Zhang, Wei Li, Mengmeng Wang, Songrui Li, Boquan Li
Summary: The allocation of tasks to unmanned aerial vehicles (UAVs) is crucial for successful search and rescue operations. This study investigates the impact of the UAV operating environment and performance on task allocation, specifically considering the effects of low-altitude wind and terrain. The study proposes models for UAV release position selection and task allocation, taking into account factors such as energy consumption and performance. The models are solved using advanced algorithms, resulting in improved calculation accuracy and optimal task completion time.
COMPUTERS & INDUSTRIAL ENGINEERING
(2022)
Article
Chemistry, Analytical
Donggeun Oh, Junghee Han
Summary: UAVs have been developed and used in various fields, especially in disaster relief. However, there are challenges in using images to search for survivors.
Article
Engineering, Aerospace
Chiranjivi Dahal, Hari Bahadur Dura, Laxman Poudel
Summary: Unmanned aerial vehicles face thrust issues in high-altitude environments. This research designed thrust-optimized blades for UAV search and rescue missions at 3,000-5,000 meters, validating their safety and practicality through experiments and CFD analysis.
INTERNATIONAL JOURNAL OF AEROSPACE ENGINEERING
(2021)
Article
Computer Science, Information Systems
Ali H. Wheeb, Rosdiadee Nordin, Asma' Abu Samah, Dimitris Kanellopoulos
Summary: The widespread usage of unmanned aerial vehicles (UAVs) in new and emerging applications requires dynamic and adaptive networking. Routing protocols for UAV ad hoc networks face challenges due to unique characteristics of UAVs, such as rapid mobility and limited energy consumption. The Optimized Link State Routing (OSLR) protocol shows promise as it offers improved delay performance. This study evaluates and examines the performance of several OLSR routing protocols in different search and rescue scenarios, and concludes that ML-OLSR outperforms other protocols in terms of packet delivery ratio, latency, energy consumption, and throughput.
Article
Computer Science, Interdisciplinary Applications
Sung Won Cho, Hyun Ji Park, Hanseob Lee, David Hyunchul Shim, Sun-Young Kim
Summary: The number of casualties in the maritime sector is increasing, and to improve the efficiency of maritime search and rescue operations, a coverage path planning method using UAVs has been proposed. This method involves a two-phase strategy to minimize search area and completion time, yielding excellent results in real flight experiments.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Computer Science, Information Systems
Sasa Sambolek, Marina Ivasic-Kos
Summary: This paper investigates the reliability of existing state-of-the-art detectors on a VisDrone benchmark and a custom-made dataset SARD, selecting the YOLOv4 detector for further examination due to its high speed, accuracy, and low false detection rate. The paper also analyzes the YOLOv4 model results related to different network sizes, detection accuracies, transfer learning settings, as well as the model's robustness to weather conditions and motion blur, proposing it as a model that can be used in SAR operations for detecting people in search and rescue scenarios.
Article
Computer Science, Information Systems
Evsen Yanmaz
Summary: In this paper, the authors focus on path planning of drone teams deployed for search and rescue missions. The paper compares joint and decoupled multi-drone path planning approaches and proposes a hybrid planner that combines the advantages of both approaches. The analysis shows that the hybrid scheme can result in better connectivity and total mission time, but may have higher mission time for very small number of search drones.
Article
Computer Science, Information Systems
Libin Hong, Yue Wang, Yichen Du, Xin Chen, Yujun Zheng
Summary: The paper proposes a method for UAV search planning problem and validates its superior performance through computational experiments.
FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING
(2021)
Article
Remote Sensing
Hisham Khalil, Saeed Ur Rahman, Inam Ullah, Inayat Khan, Abdulaziz Jarallah Alghadhban, Mosleh Hmoud Al-Adhaileh, Gauhar Ali, Mohammed ElAffendi
Summary: This paper presents a UAV-swarm-communication model using a machine-learning approach for search-and-rescue applications. The receive signal strength (RSS) and power loss of UAV communication are modeled using random forest regression, and the mathematical representation of the channel matrix is discussed. Swarm control modeling of UAVs is also studied, and a dataset for five types of triangular swarm formations is generated. K-means clustering is applied to predict the cluster, and the dendrogram of all types is investigated to obtain the correct swarm formation. Heat maps and contour plots are used to visualize the swarm clusters, and it is observed that the proposed swarms have good agreement between RSS and swarm distances.
Article
Management
Pierre Leone, Julia Buwaya, Steve Alpern
Summary: This study introduces a new type of asymmetric rendezvous search problem where one player must give the other a 'gift', which can be in the form of information or material. The research finds optimal agent paths and drop off times using families of linear programs. Applications of this work include solving other forms of rendezvous on a line and determining optimal strategies for different variations of the game.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2022)
Article
Energy & Fuels
Irfan Khan, Sanjarbek Ruzimov, Nicola Amati, Andrea Tonoli
Summary: Recent studies have shown that hybrid powertrains with dual clutch transmission are becoming more popular due to their higher efficiency, power-on shifting capability, and compact size. However, integrating an electric motor into the transmission can cause issues such as additional torque, inertia, and irregularities in operation. This paper investigates the impact of electric motor integration on the reliability of the overall system, with a focus on potential over stresses in the internal combustion engine bearings caused by bending of the gearbox primary shaft.
Article
Chemistry, Multidisciplinary
Gulnora Yakhshilikova, Ethelbert Ezemobi, Sanjarbek Ruzimov, Andrea Tonoli
Summary: This study investigates thermal limitations of small capacity and passively cooled battery packs, and discusses the use of an equivalent consumption minimization strategy with a supervisory controller. Results show that the thermal limitations increase fuel consumption and may lead to high temperatures, while the adoption of a larger capacity battery pack reduces fuel consumption.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Vittorio Mazzia, Simone Angarano, Francesco Salvetti, Federico Angelini, Marcello Chiaberge
Summary: This research introduces an attention-based Action Transformer (AcT) architecture that outperforms current mix networks in human action recognition, leveraging small temporal windows of 2D pose representations for low-latency real-time performance. Additionally, a large-scale dataset called MPOSE2021 has been open-sourced to serve as a benchmark for training and evaluating real-time, short-time HAR. The proposed methodology was extensively tested on MPOSE2021, showcasing the effectiveness of the AcT model and setting the groundwork for future HAR research.
PATTERN RECOGNITION
(2022)
Article
Chemistry, Analytical
Andrea Eirale, Mauro Martini, Luigi Tagliavini, Dario Gandini, Marcello Chiaberge, Giuseppe Quaglia
Summary: This article introduces a novel assistive robotic platform called Marvin, which combines flexible mechanical design with cutting-edge AI for perception and vocal control. Marvin is mainly used for monitoring elderly and reduced-mobility subjects, remote presence and connectivity, and night assistance. Compared to previous works, Marvin platform features a tiny omnidirectional platform and a controllable positioning device for agile mobility, effective obstacle avoidance, and extended visual range.
Article
Energy & Fuels
Shailesh Hegde, Angelo Bonfitto, Renato Galluzzi, Luis M. Castellanos Molina, Nicola Amati, Andrea Tonoli
Summary: This study introduces a novel formulation of the ECMS method in the P0 system that takes into account the power loss map of the belt drive system (BDS) and the characteristic maps of the electric machine (EM) and internal combustion engine (ICE). By using a genetic algorithm to adjust the equivalence factors of the ECMS, the proposed method aims to reduce fuel usage and CO2 emissions. Experimental results show that the use of the BDS power loss maps in the ECMS method achieved CO2 savings of 1.1 and 0.9 [g/km] in the WLTP driving cycle.
Article
Chemistry, Analytical
Luca Marchionna, Giulio Pugliese, Mauro Martini, Simone Angarano, Francesco Salvetti, Marcello Chiaberge
Summary: The game of Jenga is used as a benchmark to develop innovative manipulation solutions for complex tasks. In this study, a novel and cost-effective architecture is proposed to play Jenga using e.Do, a robotic arm, a depth camera, and a force sensor. The results show that the low-cost solution can successfully perform up to 14 consecutive block extractions.
Article
Engineering, Electrical & Electronic
Jamshid Mavlonov, Sanjarbek Ruzimov, Andrea Tonoli, Nicola Amati, Akmal Mukhitdinov
Summary: This research analyzes the electric consumption and main influencing factors of battery electric vehicles. It studies the sensitivity of energy consumption to electric motor size and efficiency map characteristics. The results show that the influences of efficiency map and electric motor size can be around 8-10% and 2-11% respectively, and the overall difference in electricity consumption can be around 10-21% when both factors are considered.
WORLD ELECTRIC VEHICLE JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Umberto Albertin, Giuseppe Pedone, Matilde Brossa, Giovanni Squillero, Marcello Chiaberge
Summary: This paper introduces an artificial intelligence-based machine learning model for detecting anomalies in factory automation systems and helping companies establish a preliminary dataset for future predictive maintenance implementation. The architecture uses a sensor fusion approach and an optimized software system to enhance computation scalability and response time. Through analysis of a digital model and two real cases, the paper demonstrates the behavior of the framework in real environments.
Article
Engineering, Mechanical
Umidjon Usmanov, Sanjarbek Ruzimov, Andrea Tonoli, Akmal Mukhitdinov
Summary: This work focuses on the development and validation of a Fuel Cell Hybrid Electric Vehicle (FCHEV) model and the comparison of different control strategies for hydrogen consumption. The model is developed using MATLAB® Simulink with a rule-based control strategy. The results are validated with experimental data and an equivalent consumption minimization strategy is implemented to optimize the control strategy. The findings show that the ECMS control strategy outperforms the rule-based one in terms of hydrogen consumption.
Article
Engineering, Mechanical
Sanjarbek Ruzimov, Luis M. Castellanos M. Molina, Renato Galluzzi, Raffaele Manca, Nicola Amati, Andrea Tonoli
Summary: This paper presents the modeling and validation of two height adjustment suspensions using concentrically and eccentrically mounted screws. It compares the performance of these solutions through simulations and experiments. The eccentric solution achieves higher overall efficiency due to the anti-rotation system and load balancing. Four prototypes are also tested on a demo vehicle for a comprehensive perspective on the eccentric mounted screw solution.
Article
Acoustics
Eugenio Tramacere, Marius Pakstys, Renato Galluzzi, Nicola Amati, Andrea Tonoli, Torbjoern A. Lembke
Summary: This paper proposes the experimental stabilization of electrodynamic maglev systems by means of passive components, providing key technological support for the Hyperloop concept of high-speed and sustainable transportation.
JOURNAL OF SOUND AND VIBRATION
(2024)
Proceedings Paper
Automation & Control Systems
Mauro Martini, Simone Cerrato, Francesco Salvetti, Simone Angarano, Marcello Chiaberge
Summary: Precision agriculture is adopting automation and robotics technology to improve agricultural efficiency. This study presents a lightweight solution for autonomous vineyard navigation using an end-to-end sensorimotor agent and deep reinforcement learning, demonstrating robustness and generalization capabilities.
2022 IEEE 18TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING (CASE)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Simone Angarano, Francesco Salvetti, Vittorio Mazzia, Giovanni Fantin, Dario Gandini, Marcello Chiaberge
Summary: Precise localization is a challenging problem, but ultra-wideband (UWB) technology offers a low-cost solution. However, non-line-of-sight conditions and complex radio environments can introduce measurement errors, so we use deep neural network optimization techniques on ultra-low-power microcontrollers to provide an effective range error mitigation solution.
INTELLIGENT COMPUTING, VOL 2
(2022)
Article
Robotics
Andrea Eirale, Mauro Martini, Marcello Chiaberge
Summary: Robot assistants and service robots are increasingly being used to support people in various environments, including healthcare and domestic settings. This research introduces a novel human-centered navigation system that combines real-time visual perception with an omnidirectional robotic platform, enabling accurate robot navigation and person monitoring.
Article
Engineering, Electrical & Electronic
Ethelbert Ezemobi, Gulnora Yakhshilikova, Sanjarbek Ruzimov, Luis Miguel Castellanos, Andrea Tonoli
Summary: The primary objective of a hybrid electric vehicle is to optimize energy consumption while considering the operating conditions of the battery. This paper proposes a strategy for energy optimization in the presence of thermal constraints, which is demonstrated through simulation results to significantly reduce energy consumption.
WORLD ELECTRIC VEHICLE JOURNAL
(2022)
