Article
Computer Science, Artificial Intelligence
Xiaoling Xu, Damian Marelli, Wei Meng, Fumin Zhang, Qianqian Cai, Minyue Fu
Summary: This paper focuses on autonomous forest full coverage search using multiple micro aerial vehicles (MAVs). The authors propose a two-stage multi-MAV forest search strategy and solve the difficulties in autonomous task allocation and path planning. Simulation results show that this method improves the efficiency of cooperative search and guarantees full area coverage.
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
(2022)
Article
Computer Science, Information Systems
Yong Li, Lihui Wang, Yuan Ren, Feipeng Chen, Wenxing Zhu
Summary: This paper focuses on the 3D spatial representation method of autonomous Micro Aerial Vehicles (MAVs) to overcome collision problems. The proposed method introduces a fast incremental inflated map construction method that reduces time-consumption and uses breadth-first search algorithms for local modification. A sliding map model is designed for large-range autonomous flight, and the effectiveness is verified with simulated and actual flight data. The proposed approach constructs the inflated map in about 3 ms with a local update range of 16 m x 16 m x 6 m.
Article
Chemistry, Multidisciplinary
Zhijian Ren, Suhan Kim, Xiang Ji, Weikun Zhu, Farnaz Niroui, Jing Kong, Yufeng Chen
Summary: This article introduces a low-voltage, high-endurance, and power-dense dielectric elastomer actuator (DEA) based on novel multiple-layering techniques and electrode-material optimization, and applies it to an aerial robot. The DEA demonstrates excellent flight performance with high lift-to-weight ratio, low hovering voltage, and long lifetime.
ADVANCED MATERIALS
(2022)
Article
Remote Sensing
Sunan Huang, Rodney Swee Huat Teo, William Wai Lun Leong
Summary: This paper investigates the issue of coverage control in multiple unmanned multirotor (MUM) systems. The existing coverage control algorithm is extended to incorporate a new downward-facing sensor model with pan-tilt-zoom (PTZ) capability, as well as new constraints for view angle and collision avoidance. The study examines mobile network coverage among the MUMs and tests the proposed scheme through computer simulations.
Article
Engineering, Civil
Jinchao Chen, Chenglie Du, Ying Zhang, Pengcheng Han, Wei Wei
Summary: Unmanned aerial vehicles (UAVs) are widely utilized in civilian and military applications for their high autonomy and strong adaptability. This paper addresses the coverage path planning problem of autonomous heterogeneous UAVs on a bounded number of regions by proposing an exact formulation based on mixed integer linear programming and a clustering-based algorithm inspired from density-based clustering methods to achieve optimal flight paths and efficient coverage tasks. Experiments demonstrating the efficiency and effectiveness of the proposed approach with randomly generated regions are conducted.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Chemistry, Analytical
Youkyung Hong, Sunggoo Jung, Suseong Kim, Jihun Cha
Summary: This study proposes a complete hardware and software architecture for autonomous area coverage missions using multiple UAVs, optimizing waypoint allocation to achieve efficient and autonomous mission execution.
Article
Computer Science, Information Systems
Shengyang Chen, Han Chen, Ching-Wei Chang, Chih-Yung Wen
Summary: The novel multilayer mapping framework, divided into awareness, local, and global layers, is implemented in different threads and supports various map outputs, providing an open-source solution for the research community.
Article
Engineering, Aerospace
Hanchen Lu, Hongming Shen, Bailing Tian, Xuewei Zhang, Zhenzhou Yang, Qun Zong
Summary: Autonomous navigation in GPS-denied environments is a challenging task for Micro-Aerial Vehicles (MAVs). This paper proposes a solution based on perception system and motion planning control system, which can achieve fast and robust MAV autonomous navigation.
AEROSPACE SCIENCE AND TECHNOLOGY
(2022)
Article
Robotics
Diego Gayango, Rafael Salmoral, Honorio Romero, Jose Manuel Carmona, Alejandro Suarez, Anibal Ollero
Summary: This letter focuses on evaluating and comparing the flapping and fixed wing flight modes on a hybrid platform for autonomous inspection operations outdoors. The platform combines the range and endurance of fixed-wing UAVs with the maneuverability and safety of flapping wing during hand launch and capture. A unified model of the platform is derived for both configurations using the Lagrange formulation to express the dynamics and aerodynamic forces. The proposed control scheme exploits the similarities in tail actuation and thrust generation to facilitate adoption on conventional autopilots. Benchmark tests and metrics are defined to evaluate and compare the performance of both modes, including energy efficiency, trajectory tracking, hand launch and capture, and accuracy in visual inspection. Experimental results validate the prototype and demonstrate the higher energy efficiency of the flapping wing mode compared to the fixed wing.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Automation & Control Systems
Tomoki Anzai, Moju Zhao, Takuzumi Nishio, Fan Shi, Kei Okada, Masayuki Inaba
Summary: This study proposes a fully autonomous pick-and-place scheme in outdoor environments using articulated aerial robots. It develops an articulated robot model with an actively tiltable sensor and designs object detection methods based on the distance between the robot and target object. A comprehensive motion strategy is developed for autonomous object searching, picking, and placing. Experimental results show the successful autonomous brick picking and placing in various outdoor environments.
IEEE ROBOTICS & AUTOMATION MAGAZINE
(2023)
Article
Engineering, Aerospace
Mingyang Lyu, Yibo Zhao, Hailong Huang
Summary: This paper focuses on the scenario of a flying robot monitoring a group of moving targets and presents a range-based navigation algorithm to solve the problem of finding the optimal position. The algorithm dynamically navigates the robot based on the estimated distances using signal strength. Simulations in Matlab and Gazebo were conducted to verify the effectiveness of the proposed approach.
Article
Robotics
D. C. Schedl, I Kurmi, O. Bimber
Summary: Autonomous drones have shown great potential in finding hidden persons in densely occluded forests during search and rescue missions. Through field experiments, it has been proven that these drones can adaptively sample and improve classification confidence, leading to quicker and more reliable detection of individuals. This technology also enables SAR operations in remote areas with unstable network coverage, ensuring effective communication with rescue teams.
Article
Computer Science, Information Systems
Baifan Chen, Siyu Li, Haowu Zhao, Limei Liu
Summary: A novel map merging method based on a suppositional box constructed by right-angled points and vertical lines is proposed. This method effectively merges maps in different scenes and achieves a successful matching rate higher than other features.
Article
Computer Science, Artificial Intelligence
Philipp Foehn, Dario Brescianini, Elia Kaufmann, Titus Cieslewski, Mathias Gehrig, Manasi Muglikar, Davide Scaramuzza
Summary: This paper presents a novel system for autonomous, vision-based drone racing, achieving second place at the 2019 AlphaPilot Challenge by combining learned data abstraction, nonlinear filtering, and time-optimal trajectory planning.
Article
Engineering, Civil
Fatemeh Rekabi-Bana, Junyan Hu, Tomas Krajnik, Farshad Arvin
Summary: This paper presents a unified robust path planning, optimal trajectory generation, and control architecture for a quadrotor coverage mission. The proposed algorithm uses a modified probabilistic roadmap and a recursive node and link generation scheme to achieve safe navigation in uncertain environments. Optimal trajectory generation and robust control policy compensate for uncertainties and disturbances in accomplishing the coverage mission.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
G. Kyprianou, L. Doitsidis, S. A. Chatzichristofis
Summary: Recent advances in technology have led to the widespread use of robotic systems in the modern working environment, particularly the increased appeal of multi-robot teams. However, path planning for multiple robotic systems (MRS) in dynamic environments poses significant challenges that require further research and development.
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
(2022)
Article
Robotics
Yunlong Song, Davide Scaramuzza
Summary: A novel framework of policy search for model predictive control is proposed in the study, utilizing policy search to automatically select high-level decision variables for MPC. The formulation of a parameterized controller allows optimizing policies in a self-supervised manner.
IEEE TRANSACTIONS ON ROBOTICS
(2022)
Article
Robotics
Philipp Foehn, Elia Kaufmann, Angel Romero, Robert Penicka, Sihao Sun, Leonard Bauersfeld, Thomas Laengle, Giovanni Cioffi, Yunlong Song, Antonio Loquercio, Davide Scaramuzza
Summary: Agilicious is a hardware and software framework designed for autonomous, agile quadrotor flight, supporting both model-based and neural network-based controllers. It offers a combination of high-performance hardware and flexible software stack, making it suitable for various tasks and environments, as well as hardware-in-the-loop simulation.
Article
Robotics
Miguel Castillon, Pere Ridao, Roland Siegwart, Cesar Cadena
Summary: In this paper, a non-rigid registration method is proposed to handle motion distortion in robot scans. By leveraging the continuous and smooth motion of the robot, computational complexity is reduced while accuracy is improved. Benchmark tests using synthetic and real data are conducted, and the source code for the algorithm is made publicly available.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Eugenio Cuniato, Nicholas Lawrance, Marco Tognon, Roland Siegwart
Summary: In this work, a safety layer for mechanical systems is proposed to detect and respond to unstable dynamics caused by external disturbances. The system actively computes the Largest Lyapunov Exponent (LLE) to detect potentially dangerous behaviors and imposes power limit constraints using Control Barrier Functions (CBFs). The proposed architecture is experimentally validated on an Omnidirectional Micro Aerial Vehicle (OMAV).
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Rene Zurbruegg, Hermann Blum, Cesar Cadena, Roland Siegwart, Lukas Schmid
Summary: This study presents an embodied agent with an adaptive semantic segmentation network that can autonomously adapt to new indoor environments. By collecting images of the new environment and utilizing self-supervised domain adaptation, the agent can quickly and safely gather relevant data. Experiments demonstrate that our method achieves faster adaptation and higher performance compared to an exploration objective.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Giuseppe Rizzi, Jen Jen Chung, Abel Gawel, Lionel Ott, Marco Tognon, Roland Siegwart
Summary: In this article, we explore and utilize sampling-based control techniques to tackle the challenging task of mobile manipulation of articulated objects. Manipulation tasks involve handling non-differentiable switching contact dynamics, posing limitations to traditional gradient-based optimization methods. Sampling-based techniques offer relief to these limitations but do not guarantee the stability and constraints of robots. Therefore, we introduce a novel framework that combines sampling-based control, control barrier functions, and passivity theory to enhance the safety and robustness of robotic manipulation. We also provide practical insights for the robust deployment of stochastic control on a conventional CPU and share our generic and multithreaded implementation as an open-source resource.
IEEE TRANSACTIONS ON ROBOTICS
(2023)
Article
Computer Science, Artificial Intelligence
Emmanuel K. Raptis, Marios Krestenitis, Konstantinos Egglezos, Orfeas Kypris, Konstantinos Ioannidis, Lefteris Doitsidis, Athanasios Ch. Kapoutsis, Stefanos Vrochidis, Ioannis Kompatsiaris, Elias B. Kosmatopoulos
Summary: This paper presents a novel Precision Agriculture platform that addresses the limited battery life issue by designing missions tailored to each field's specific characteristics. The system is capable of designing coverage missions for any type of UAV, considering field shape and obstacles. It also includes automated image processing and weed detection using a deep learning module. The effectiveness of the platform was validated through extensive experimentation in cotton fields in Larissa, Greece.
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
(2023)
Article
Robotics
Andrei Cramariuc, Lukas Bernreiter, Florian Tschopp, Marius Fehr, Victor Reijgwart, Juan Nieto, Roland Siegwart, Cesar Cadena
Summary: The integration of multiple sensor modalities and deep learning into SLAM systems is an important area of research. It enables robustness in challenging environments and interoperability of heterogeneous multi-robot systems. Maplab 2.0 provides an open-source platform for developing and integrating new modules and features into a fully-fledged SLAM system. Extensive experiments show that maplab 2.0 achieves comparable accuracy to the state-of-the-art benchmark and demonstrates flexibility in various use cases.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Robotics
Lintong Zhang, Michael Helmberger, Lanke Frank Tarimo Fu, David Wisth, Marco Camurri, Davide Scaramuzza, Maurice Fallon
Summary: To drive the advancement of SLAM systems, we created the Hilti-Oxford Dataset, which includes various challenges to test the performance of SLAM algorithms in different scenarios. We implemented a novel ground truth collection method to accurately measure pose errors with millimeter accuracy. The dataset attracted a large number of researchers to participate in the Hilti SLAM challenge.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Robotics
Liang Zhang, Zexu Zhang, Roland Siegwart, Jen Jen Chung
Summary: This article addresses the problem of active planning for cooperative localization in multirobot systems under measurement uncertainty. An adaptive power series expansion algorithm is developed to accurately predict future connection probabilities, improving planning performance under uncertainty.
IEEE TRANSACTIONS ON ROBOTICS
(2023)
Article
Engineering, Civil
Kuanqi Cai, Weinan Chen, Daniel Dugas, Roland Siegwart, Jen Jen Chung
Summary: This paper addresses the problem of autonomous pedestrian-aware navigation in shared human-robot environments and proposes a flow map-based RRT* method (FM-RRT*) to solve it. The method models the velocity of pedestrian flow and the area where the robot is less invasive, and uses adaptive bias sampling to drive the robot considering relative velocity or minimal intrusion. The evaluation conducted in the Crowdbot Challenge simulator shows that the method can find a feasible path while avoiding intrusive human movement.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Automation & Control Systems
Simon L. Jeger, Nicholas Lawrance, Florian Achermann, Oscar Pang, Mirko Kovac, Roland Y. Siegwart
Summary: Autonomous ballooning presents challenges for planning and control algorithms due to limited control capabilities, the stochastic nature of balloon flight caused by wind, and the difficulty of sensing wind remotely. This study uses reinforcement learning to develop a control policy for autonomous balloon navigation in a varying wind field. The approach is evaluated through simulations and indoor and outdoor experiments, demonstrating successful navigation towards target positions with minimal distance errors.
IEEE ROBOTICS & AUTOMATION MAGAZINE
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Stepan Tulyakov, Alfredo Bochicchio, Daniel Gehrig, Stamatios Georgoulis, Yuanyou Li, Davide Scaramuzza
Summary: This study addresses several issues in video frame interpolation, including unstable fusion process of complementary interpolation results, inefficient motion estimation process, and potential artifacts in low contrast regions. Additionally, a large-scale dataset with challenging scenes is constructed, and the reconstruction quality is improved through multi-scale feature-level fusion and one-shot non-linear inter-frame motion computation.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Simon Schaefer, Daniel Gehrig, Davide Scaramuzza
Summary: This research introduces a novel event-processing paradigm called Asynchronous, Event-based Graph Neural Networks (AEGNNs), which generalize standard GNNs to process events as evolving spatio-temporal graphs. AEGNNs significantly reduce computation and latency by only recomputing network activations for the nodes affected by each new event. The experimental results show a reduction in computational complexity by up to 200-fold and similar or even better performance compared to state-of-the-art asynchronous methods, making AEGNNs a promising approach for low-latency event-based processing.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)