Article
Computer Science, Artificial Intelligence
David M. Bossens, Danesh Tarapore
Summary: This article introduces an algorithm called QED, which enhances the quality of evolved archives by inducing behavioral diversity through introducing environmental diversity, leading to improved recovery capability for robot swarms when facing faults. The study shows that the archives evolved by QED outperform traditional behavioral descriptors in 5 different robot swarm benchmark tasks.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2021)
Article
Computer Science, Artificial Intelligence
Antoine Ligot, Andres Cotorruelo, Emanuele Garone, Mauro Birattari
Summary: This article proposes an experimental protocol for comparing fully automatic design methods for robot swarms, including defining benchmarks and sampling strategies, to address the lack of systematic analysis and comparison in the optimization-based design of robot swarms.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2022)
Article
Multidisciplinary Sciences
Bryan VanSaders, Sharon C. Glotzer
Summary: The study showed that embedding particles with variable diameters in colloidal monolayers can produce significant plastic slip, allowing the reshaping of colloidal matter through biased dislocation emitters. This method is also applicable to larger-scale swarms of robotic particles organizing into dense ordered 2D arrangements.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2021)
Article
Computer Science, Artificial Intelligence
Fernando J. Mendiburu, David Garzon Ramos, Marcos R. A. Morais, Antonio M. N. Lima, Mauro Birattaria
Summary: This paper presents Mate, an automatic off-line design method for spatially-organizing behaviors in robot swarms. Experimental results show that Mate outperforms other automatic design methods in handling tasks with spatial distribution constraints.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Chemistry, Multidisciplinary
Alexandre Campo, Stamatios C. Nicolis, Jean-Louis Deneubourg
Summary: Remembering information is crucial for adaptation and behavior adjustment in both living organisms and artificial systems. Pavlov's experiments demonstrate how single animals can trigger behavioral responses based on memory of stimuli associated with rewards. Researchers propose a novel behavior based on aggregation process to enable robotic swarm to exhibit collective memory.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Ken Hasselmann, Antoine Ligot, Mauro Birattari
Summary: Several methods have been proposed for automatically designing control software for robot swarms by assembling predefined modules. However, these methods always require manual definition of the modules, which is time consuming and requires expertise. In this study, a novel approach called Nata is introduced, which automatically generates neural networks as modules using a quality diversity evolutionary algorithm. The generated modules are used to assemble probabilistic finite-state machines for controlling the robot swarms. The approach is demonstrated on three missions in both simulation and with real robots. Nata is the first method that automatically generates and assembles modules for control software design.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Information Systems
Yuan Xu, Gelei Deng, Tianwei Zhang, Han Qiu, Yungang Bao
Summary: The development of robotics technology is accelerated by strong support from cloud computing, but also faces potential DoS threats. This paper introduces new DoS attack methods and demonstrates their severity through evaluations and case studies, urging the robotics community to enhance security measures and performance in cloud-robotic systems.
INFORMATION SCIENCES
(2021)
Article
Chemistry, Multidisciplinary
Dario Albani, Wolfgang Honig, Daniele Nardi, Nora Ayanian, Vito Trianni
Summary: Complex service robotics scenarios involve unpredictable task appearances in space and time, requiring robots to continuously relocate and balance motion costs and efficiency. Decentralized solutions are needed for large-scale problems to allow robotic systems to self-organize and adapt to task demands efficiently. A proposed approach combines collective decision-making for task allocation and search-based path planning for robot swarms, showing improvements over baseline algorithms in specific settings and robustness to communication limitations and robot failures.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Hardware & Architecture
Zhe Ban, Junyan Hu, Barry Lennox, Farshad Arvin
Summary: This paper proposes an extended model of a self-organised flocking mechanism using heterogeneous swarm system, ensuring a collision-free flocking trajectory for the followers. In addition, an optimal control model is developed to steer the swarm to a desired goal location, with less requirement for power and storage compared to conventional methods.
MOBILE NETWORKS & APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Peter Travis Jardine, Sidney N. Givigi
Summary: This paper introduces a bimodal control strategy for transitioning between different flocking and dynamic structures. The strategy is designed for applications where agents need to pursue and close in on a target before performing complex tasks. It defines a new method called dynamic enspherement, which combines consensus-based flocking with target pursuit and capturing. The proposed approach is validated through simulations on particles with double-integrator dynamics.
Article
Computer Science, Information Systems
Sanghyeon Bae, Sunghyeon Joo, Junhyeon Choi, Jungwon Pyo, Hyunjin Park, Taeyong Kuc
Summary: Multi-robot systems face the challenge of simultaneously considering robot movement and influence while planning tasks. This paper proposes a semantic knowledge-based hierarchical planning approach that extends knowledge by considering interactions between environmental elements. The task planner utilizes spatial hierarchy knowledge to group robots and generate optimal task plans for each group.
Article
Robotics
Enrica Soria, Fabrizio Schiano, Dario Floreano
Summary: Recent works in aerial robotics have shown that swarms of robots can achieve self-organized and cohesive flight through the exchange of local information. This paper proposes a distributed predictive swarm model that generates self-organized, safe, and cohesive trajectories in real-time. Simulation and real-world experiments demonstrate the feasibility of the method.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Luigi Feola, Vito Trianni
Summary: This study improves task execution by using adaptive behavioral strategies for decentralized robotic swarms. A probabilistic approach is used to enable opportunistic team formation for minimalist agents unable to communicate and plan ahead. Experiments with simulated and real swarms demonstrate the effectiveness of the proposed approach, with potential applications in micro/nano-robotics.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Tanja Katharina Kaiser, Heiko Hamann
Summary: Applications of large-scale mobile multirobot systems have advantages in terms of robustness and scalability. Developing controllers for these systems is challenging, and automatic design using machine learning or evolutionary robotics can be a solution. However, the challenge lies in designing reward or fitness functions. Innate motivation approaches, such as minimizing surprise, can be used to avoid specific rewards and work with different drivers like curiosity. The unique advantage of swarm robot cases is that swarm members can trigger more active behaviors in a self-referential loop.
IEEE TRANSACTIONS ON ROBOTICS
(2022)
Article
Robotics
Nathalie Majcherczyk, Daniel Jeswin Nallathambi, Tim Antonelli, Carlo Pinciroli
Summary: The letter introduces an approach to distributed storage and fusion of data for collective perception in resource-limited robot swarms demonstrated in a distributed semantic classification scenario. The main contributions include a decentralized data structure and algorithm designed for low-resource mobile robots to efficiently store annotations and reduce variance in annotations calculation. Realistic simulated experiments were conducted to evaluate the performance of the approach.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Chemistry, Analytical
Silvia Terrile, Jesus Miguelanez, Antonio Barrientos
Summary: Haptic technology enhances virtual reality experiences, and the development of a soft haptic glove allows for more natural kinesthetic perception of hand movements. Testing of the glove showed satisfactory results in terms of both functionality and user comfort.
Article
Engineering, Aerospace
Eduardo Gallo, Antonio Barrientos
Summary: This article proposes an inertial navigation algorithm to mitigate the negative consequences of the absence of GNSS signals on autonomous fixed wing UAVs. The algorithm utilizes multiple sensors to improve attitude error and position drift, facilitating fusion with visual odometry algorithms.
AEROSPACE SCIENCE AND TECHNOLOGY
(2022)
Article
Chemistry, Analytical
Christyan Cruz Ulloa, Guillermo Prieto Sanchez, Antonio Barrientos, Jaime Del Cerro
Summary: Recent technological breakthroughs have revolutionized fields such as machine vision and search and rescue robotics, with the application of new and improved neural networks combined with modern optical sensors like thermal cameras for victim identification in post-disaster environments. Robotic teams equipped with specific sensors have been developed for primary intervention tasks in high-risk post-disaster environments. Through testing and validation, a novel automatic method utilizing thermal image processing and CNN has shown over 90% efficiency in victim identification.
Editorial Material
Chemistry, Multidisciplinary
Juan Jesus Roldan-Gomez, Antonio Barrientos
APPLIED SCIENCES-BASEL
(2021)
Article
Agronomy
Constantino Valero, Anne Krus, Christyan Cruz Ulloa, Antonio Barrientos, Juan Jose Ramirez-Montoro, Jaime del Cerro, Pablo Guillen
Summary: This research developed a new cropping system for precise fertilization of plants using optical sensors and actuation system, avoiding traditional local fertilization methods. Multispectral cameras and LiDAR devices were used to detect plant health status and three-dimensional characteristics for accurate determination of fertilization needs.
Article
Chemistry, Analytical
Eduardo Gallo, Antonio Barrientos
Summary: This article introduces the sensor suite used in the navigation systems of autonomous aircraft, including accelerometers, gyroscopes, magnetometers, GNSS receivers, air data systems, and digital cameras. It also presents realistic and customizable models for these sensors and the camera, allowing non-experts to easily generate realistic results.
Article
Mathematics
Diego Cerrillo, Antonio Barrientos, Jaime Del Cerro
Summary: This article provides a general overview of the different approaches to modeling hyper-redundant cable-driven robots and proposes a guide to help researchers decide which methodology to apply. It introduces a framework and mathematical equations for the underlying models, and offers a step-by-step tutorial by applying it to three real robots.
Article
Chemistry, Analytical
Christyan Cruz Ulloa, David Dominguez, Jaime Del Cerro, Antonio Barrientos
Summary: Quadruped robots have been a focus of technological study and development, especially in applications requiring high mobility skills like Search and Rescue tasks. Integrating a manipulator arm and using Mixed Reality technology can improve control efficiency and operator decision-making confidence for the robotic set.
Article
Engineering, Multidisciplinary
Silvia Terrile, Andrea Lopez, Antonio Barrientos
Summary: Soft bioinspired manipulators have numerous degrees of freedom, but their control is complex, especially when modeling the elastic elements that define their structure. Finite elements offer accurate models but are not suitable for real-time use. Machine Learning (ML) presents a potential solution, but it requires extensive training experiments. A combination of Finite Element Analysis (FEA) and ML can be a promising approach. This study presents the implementation of a real robot with flexible modules actuated by shape memory alloy (SMA) springs, developing its FEA-based model, tuning a neural network, and evaluating the results.
Article
Engineering, Aerospace
Eduardo Gallo, Antonio Barrientos
Summary: This article proposes a method to reduce the horizontal position drift in the absence of GNSS signals experienced by the VNS on a UAV by using prior information based on the outputs of the INS. The method achieves significant reductions in drift and is evaluated through Monte Carlo simulations of GNSS signal loss scenarios. The authors provide open-source software for the navigation algorithms and simulations.
Article
Chemistry, Analytical
David Orbea, Christyan Cruz Ulloa, Jaime Del Cerro, Antonio Barrientos
Summary: This paper proposes RUDE-AL (Roped UGV DEployment ALgorithm) for sinkhole exploration tasks and assistance to potential trapped victims. It utilizes a combination of four mobile robots and a cable-driven parallel robot (CDPR), and uses genetic algorithms to generate optimal target routes for each mobile robot.
Article
Engineering, Multidisciplinary
Christyan Cruz Ulloa, Lourdes Sanchez, Jaime Del Cerro, Antonio Barrientos
Summary: Researchers have developed a bio-inspired locomotion method for robots using a central pattern generator and convolutional neural networks, allowing quadruped robots to overcome unstructured terrains and successfully identify and overcome obstacles. Experimental results showed that the proposed method had an efficiency rate of over 93% for terrain characterization and over 91% success rate in overcoming unstructured terrains.
Proceedings Paper
Robotics
Christyan Cruz Ulloa, Miguel Garcia, Jaime del Cerro, Antonio Barrientos
Summary: This article analyzes the effectiveness of using robotic interventions in post-disaster environments for search and rescue explorations. By applying neural network models and image detection algorithms, victims can be detected early, optimizing the identification time and safeguarding rescuers. The models obtained from training with both real and synthetic images have been validated through tests and exercises, showing that they are applicable in real environments.
ROBOT2022: FIFTH IBERIAN ROBOTICS CONFERENCE: ADVANCES IN ROBOTICS, VOL 2
(2023)
Proceedings Paper
Robotics
Christyan Cruz Ulloa, David Dominguez, Antonio Barrientos, Jaime del Cerro
Summary: Technological development has advanced the robotics field, resulting in the application of quadruped robots in search and rescue tasks. This study focuses on teleoperating a quadruped robot equipped with a six-degree-of-freedom manipulator using Mixed Reality, aiming to improve the efficiency of handling and transporting medical equipment in post-disaster situations. Simulations and field tests demonstrate the effectiveness of the proposed system, showing a 21% increase in efficiency compared to conventional interfaces.
ROBOTICS IN NATURAL SETTINGS, CLAWAR 2022
(2023)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Christyan Cruz Ulloa, Anne Krus, Guido Torres Llerena, Antonio Barrientos, Jaime Del Cerro, Constantino Valero
Summary: Interfaces for human-robot interaction in precision agriculture have been used to improve production processes and apply specialized treatments for specific plant needs. The Sureveg Core Organic COfound ERA-Net project implemented a robotic platform with sensory, actuation, and communication systems to develop a human-machine interface for fertilization actions. The tests conducted showed positive results in vegetable production.
TRENDS IN ARTIFICIAL INTELLIGENCE AND COMPUTER ENGINEERING (ICAETT 2021)
(2022)