Review
Computer Science, Artificial Intelligence
Xi Hu, Rayan H. Assaad
Summary: The increasing computational power of machines and more affordable robotic hardware and software offer great opportunities for developing more advanced intelligent robotic systems to perform numerous tasks in the civil infrastructure sector. However, the existing information on the applications of UAVs and UGVs in civil infrastructure mainly focuses on specific domains or provides a broad summary without sufficient details about sensing devices and data processing techniques. Therefore, this paper provides a systematic review of UAVs and UGVs in the civil infrastructure sector, aiming to collect relevant information, synthesize current knowledge, and identify challenges and opportunities for future studies and engineering practices.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Automation & Control Systems
Markus Ryll, Davide Bicego, Mattia Giurato, Marco Lovera, Antonio Franchi
Summary: FAST-Hex is a micro aerial hexarotor platform that can adapt its configuration between under-actuated and fully actuated states. It features a lightweight mechanical structure and a flexible motion controller for efficient pose tracking. Through experimental validation, the control performance of FAST-Hex is demonstrated.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Automation & Control Systems
William Stewart, Enrico Ajanic, Matthias Mueller, Dario Floreano
Summary: This article introduces a novel avian-inspired grasping mechanism that allows winged UAVs to grasp an object while flying. Experimental results show that the claw can close in under half a second and the loads encountered during the grasp event have negligible impact on the UAV.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Automation & Control Systems
William Stewart, Enrico Ajanic, Matthias Mueller, Dario Floreano
Summary: This article introduces a novel avian-inspired grasping mechanism that allows winged UAVs to grasp an object while flying, without the need to land and stop. Experimental results show that grasping small objects during flight has a negligible impact on the vehicle.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Robotics
Anibal Ollero, Marco Tognon, Alejandro Suarez, Dongjun Lee, Antonio Franchi
Summary: This article primarily analyzes the evolution and current trends in aerial robotic manipulation, covering different types of aircraft equipped with various robotic manipulators, including cooperative manipulation and multibody design, and finally presenting the vision of future new generation aerial robotic manipulators.
IEEE TRANSACTIONS ON ROBOTICS
(2022)
Article
Automation & Control Systems
HaoTse Hsiao, Jiefeng Sun, Haijie Zhang, Jianguo Zhao
Summary: This article presents a mechanically intelligent and passive (MIP) gripper that can be used for aerial perching or grasping without any actuator. The gripper has a mechanical mechanism for dampening impact and robustly grasping objects. Static models are established to predict the required forces for successful state transitions, and design guidelines are developed for the gripper to be adaptable to different flying robots with varying weights. Experiments validate the models, demonstrating the gripper's capability for aerial perching and grasping.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Robotics
W. R. T. Roderick, M. R. Cutkosky, D. Lentink
Summary: The researchers developed a biomimetic robot based on how birds take off, land, and grasp, allowing it to dynamically perch on complex surfaces and grasp irregular objects. The robot passively transforms impact energy into grasp force and uses an underactuated grasping mechanism to quickly grasp irregularly shaped objects.
Article
Robotics
Pham H. Nguyen, Karishma Patnaik, Shatadal Mishra, Panagiotis Polygerinos, Wenlong Zhang
Summary: Current aerial robots have limited interaction capabilities in unstructured environments compared to their biological counterparts. This includes problems with collision tolerance, landing or perching on objects with unknown properties, and the added weight of external mechanical impact protection which reduces agility and flight time. In this work, a lightweight, inflatable, soft-bodied aerial robot (SoBAR) is proposed, which can vary its body stiffness to achieve intrinsic collision resilience. SoBAR demonstrates its ability to endure and recover from collisions in different directions, and also improves perching success rates. Additionally, a hybrid fabric-based bistable (HFB) grasper is used to perform contact-reactive grasping using impact energies. The collision resilience, impact absorption, and manipulation capabilities of SoBAR with the HFB grasper are thoroughly studied and compared to conventional aerial robots.
Article
Automation & Control Systems
Bjorn Lindqvist, Samuel Karlsson, Anton Koval, Ilias Tevetzidis, Jakub Haluska, Christoforos Kanellakis, Ali-akbar Agha-mohammadi, George Nikolakopoulos
Summary: This work presents a field-hardened autonomous multimodal legged-aerial robotic system for subterranean exploration. The robotic system combines a legged robot with an aerial platform to meet the requirements of large-scale and long-term missions. The system has been evaluated in real subterranean tunnel areas for fully autonomous search-and-rescue missions, aiming to identify and locate objects of interest within the subterranean environment.
ROBOTICS AND AUTONOMOUS SYSTEMS
(2022)
Article
Chemistry, Analytical
Panagiotis Rousseas, George C. Karras, Charalampos P. Bechlioulis, Kostas J. Kyriakopoulos
Summary: In this study, a reactive algorithm is developed for multiple autonomous multi-rotor robots to explore indoor unknown environments. The algorithm utilizes an Artificial-Harmonic Potential Field (AHPF) for navigation and a low-level tracking controller. The effectiveness of the algorithm is validated through high-fidelity simulations.
Review
Energy & Fuels
Tom Verstraten, Md Sazzad Hosen, Maitane Berecibar, Bram Vanderborght
Summary: Untethered robots rely on battery packs for power supply, and this paper proposes criteria to evaluate the suitability of different battery technologies for robotic applications. It evaluates and compares the capabilities of relevant battery technologies, discusses current limitations and new technological developments, and highlights opportunities for interdisciplinary research between battery technology and robotics.
Article
Robotics
Drew Hanover, Philipp Foehn, Sihao Sun, Elia Kaufmann, Davide Scaramuzza
Summary: This paper proposes a novel hybrid adaptive nonlinear model predictive control (NMPC) method called L-1-NMPC, which learns and compensates for model uncertainties online to improve performance of quadrotor flight in challenging environments. The method demonstrates high flexibility and robustness, achieving significant tracking error reduction and improved adaptability in the presence of complex aerodynamic effects and unknown disturbances.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Computer Science, Information Systems
Fran Real, Angel R. Castano, Arturo Torres-Gonzalez, Jesus Capitan, Pedro J. Sanchez-Cuevas, Manuel J. Fernandez, Manuel Villar, Anibal Ollero
Summary: This article introduces a team of multiple UAVs to perform cooperative missions, including building a wall with bricks. The novel architecture and design allow the UAVs to pick, transport, and place bricks, which can be extended to other multi-UAV applications involving physical interaction.
Article
Mathematics, Interdisciplinary Applications
Zain Anwar Ali, Amber Israr, Eman H. Alkhammash, Myriam Hadjouni
Summary: The study presents an adaptive hybrid controller for the formation control of multiple UAVs leader-follower configurations with communication delay, bridging the gap in existing research that lacks delay incorporation and adaptability. The strategy involves an adaptive fuzzy logic controller and a PID controller, with the former fine-tuning the gains of the latter, showing robustness and meeting mission requirements. The main contribution lies in achieving stable formation, optimal error range, and manageable time delays throughout the flight.
Article
Robotics
Fabrizio Schiano, Przemyslaw Mariusz Kornatowski, Leonardo Cencetti, Dario Floreano
Summary: This study proposes a reconfigurable drone based on a modular design, which can adapt to different cargo shapes, sizes, and mass by automatically generating drone configurations and suitable flight controller parameters. This design represents a cheaper and more versatile alternative solution.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Automation & Control Systems
Jiawei Meng, Yuanchang Liu, Richard Bucknall, Weihong Guo, Ze Ji
Summary: In this paper, a new algorithm called anisotropic GPMP2 is proposed to revolutionize motion planning for USVs. The algorithm integrates anisotropy and dynamic fast GP interpolation to reduce energy consumption and improve computational speed and trajectory quality.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2022)
Article
Agronomy
Xiuguo Zou, Siyu Wang, Yan Qian, Fei Gong, Shixiu Zhang, Jiangxue Hu, Wenchao Liu, Yuanyuan Song, Shikai Zhang, Jiawei Meng, Xinfa Qiu
Summary: This study improves the efficiency of broiler breeding through simulation of ammonia concentration distribution and structural modification.
Article
Chemistry, Analytical
Xiuguo Zou, Chenyang Wang, Manman Luo, Qiaomu Ren, Yingying Liu, Shikai Zhang, Yungang Bai, Jiawei Meng, Wentian Zhang, Steven W. Su
Summary: In this study, an electronic nose detection system based on KNN-SVM was designed for apple quality grading. By optimizing the nasal cavity structure and reducing data dimension using PCA and LDA, the classifier achieved improved accuracy.
Article
Engineering, Civil
Jiawei Meng, Ankita Humne, Richard Bucknall, Brendan Englot, Yuanchang Liu
Summary: Unmanned surface vehicles are becoming increasingly important in various sectors of the maritime industry, offering more operational flexibility. This article proposes a novel motion planner, GPMP2*, and a fully-autonomous framework based on ROS for an advanced USV.
IEEE JOURNAL OF OCEANIC ENGINEERING
(2023)
Editorial Material
Robotics
Joao Bimbo, Minas Liarokapis, Monica Malvezzi, Gionata Salvietti
FRONTIERS IN ROBOTICS AND AI
(2023)
Article
Automation & Control Systems
Vatsal V. Patel, Minas V. Liarokapis, Aaron M. Dollar
Summary: Technologies from open source projects have been widely adopted in robotics in recent years. Open source hardware lowers the barrier of entry to new technologies and can accelerate innovation in robotics. This work provides a review on open robot hardware (ORH), highlighting the benefits and challenges encountered by users and developers, and offering best practices for successful ORH development, based on a survey of over 80 major ORH projects and initiatives.
IEEE ROBOTICS & AUTOMATION MAGAZINE
(2023)
Article
Computer Science, Information Systems
Joao Buzzatto, Minas Liarokapis
Summary: The paper presents the Omnirotor platform, a versatile, multi-modal, coaxial, tilt-rotor, all-terrain vehicle that combines an UAV and an UGV. It discusses the design, development, and experimental validation of the platform, highlighting its capabilities in traversing challenging environments and unstructured terrains, as well as its ground manipulation capabilities. The Omnirotor offers exciting prospects for applications in search-and-rescue scenarios, surveillance, and aerial and ground manipulation.
Article
Computer Science, Information Systems
Ricardo V. Godoy, Bonnie Guan, Felipe Sanches, Anany Dwivedi, Minas Liarokapis
Summary: This study compares the performance of three different approaches in developing EMG-based hand gesture decoding models and finds that training a subject-specific deep learning model from scratch achieves higher decoding accuracy with larger datasets, while the few-shot learning approach produces more robust results and better performance with smaller datasets or in scenarios where long data collection sessions are not possible or multiple users are intended for the interface.
Proceedings Paper
Automation & Control Systems
Joao Buzzatto, Mojtaba Shahmohammadi, Junbang Liang, Felipe Sanches, Saori Matsunaga, Rintaro Haraguchi, Toshisada Mariyama, Bruce MacDonald, Minas Liarokapis
Summary: This work introduces a soft robotic gripper based on kirigami, studies its behavior and development, and compares different designs through experiments. The findings indicate a clear relationship between reconfiguration degree and grasping force, and are used to design an improved version of the gripper using simple manufacturing methods.
2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
(2022)
Proceedings Paper
Automation & Control Systems
Che-Ming Chang, Felipe Sanches, Geng Gao, Amantha Johnson, Minas Liarokapis
Summary: To meet the communication needs of the deafblind, an assistive technology was developed to translate and replicate American Sign Language using tactile sign language and robots. The system's performance was evaluated through tactile sign recognition by a blind user and its accuracy with novice users.
2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
(2022)
Proceedings Paper
Automation & Control Systems
Ricardo V. Godoy, Anany Dwivedi, Mojtaba Shahmohammadi, Minas Liarokapis
Summary: Researchers have traditionally relied on complex hardware systems and specialized signal processing methods for the development of muscle-machine interfaces (MuMIs). In this work, a novel MuMI called Lightmyography (LMG) is proposed, which aims to overcome the limitations of previous approaches. Two deep learning techniques, Temporal Multi-Channel Transformer (TMC-T) and Temporal Multi-Channel Vision Transformer (TMC-ViT), are employed to improve the performance of LMG-based hand gesture classification. Additionally, the influence of varying parameters during the training phase is investigated, and data augmentation techniques are used to enhance the efficiency of deep learning models.
2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
(2022)
Proceedings Paper
Automation & Control Systems
Geng Gao, Junbang Liang, Minas Liarokapis
Summary: This study presents a mechanically programmable, variable stiffness, jamming actuator based on an articulated mesh structure, which can achieve elastic deformation and compress into a pre-programmed shape under pressure. The actuator can be used to develop variable stiffness joints and wearable elbow exoskeleton systems, expanding the possibilities for the application of soft robots.
2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
(2022)
Proceedings Paper
Engineering, Biomedical
Ricardo V. Godoy, Gustavo J. G. Lahr, Anany Dwivedi, Tharik J. S. Reis, Paulo H. Polegato, Marcelo Becker, Glauco A. P. Caurin, Minas Liarokapis
Summary: With the increasing use of robotic and bionic devices, EMG-based interfaces are explored for intuitive interactions. However, extracting appropriate features from raw EMG signals is crucial for excellent performance. To address this issue, this study proposes a deep learning technique called Temporal Multi-Channel Vision Transformers, which can automatically extract complex features from raw EMG data and potentially achieve dexterous control of robots and bionic hands.
2022 9TH IEEE RAS/EMBS INTERNATIONAL CONFERENCE ON BIOMEDICAL ROBOTICS AND BIOMECHATRONICS (BIOROB 2022)
(2022)
Proceedings Paper
Computer Science, Cybernetics
Jayden Chapman, Anany Dwivedi, Minas Liarokapis
Summary: This work presents a 16 degree of freedom robotic hand designed for increased dexterity and minimal cost. The hand utilizes a combination of direct driven and tendon driven systems, allowing for complex thumb trajectories and improved thumb dexterity. Experimental validation demonstrates the effectiveness of the device in kinematics, grasping, and manipulation tasks.
2022 IEEE-RAS 21ST INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS (HUMANOIDS)
(2022)
Proceedings Paper
Computer Science, Cybernetics
Nathan Elangovan, Che-Ming Chang, Ricardo Godoy, Felipe Sanches, Ke Wang, Patrick Jarvis, Minas Liarokapis
Summary: This study focuses on comparing human and robot performance in complex kitchen tasks and evaluating the required grasping and dexterous manipulation skills. By analyzing a dataset, a taxonomy is proposed to classify the attributes of kitchen-specific grasping and manipulation strategies, along with benchmarks for comparing robotic grippers against human counterparts.
2022 IEEE-RAS 21ST INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS (HUMANOIDS)
(2022)