Article
Automation & Control Systems
Javier Munoz, Blanca Lopez, Fernando Quevedo, Santiago Garrido, Concepcion A. Monje, Luis E. Moreno
Summary: This study combines the Fast Marching Square path planning technique with Gaussian processes (GP) machine learning method to tackle the challenge of exploring unknown environments in robotics. The Fast Marching Square method is used to identify the least explored areas and plan the vehicle's path. The GP model predicts unexplored regions based on the collected data. The use of UAVs for exploration and surveillance has increased due to their sensor capabilities and versatility. By assigning weights to each method, the UAV can focus on points with more interesting or unexplored data. The study examines the impact of these weights on the GP model's mean absolute error and predictive variance and tests the algorithm on a real environment from a satellite image. The results demonstrate that an accurate depiction of the environment can be generated much faster compared to traditional methods like the Boustrophedon.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Automation & Control Systems
Danial Sufiyan, Luke Soe Thura Win, Shane Kyi Hla Win, Ying Hong Pheh, Gim Song Soh, Shaohui Foong
Summary: This study discusses the development of a multimodal, nature-inspired unmanned aerial vehicle (UAV) that can operate in three different flight modes. The UAV achieves efficient hover through a nature-inspired method and has the flexibility to enter more agile states using additional modes. The study documents the mechanical configuration and software/control architecture used to enable the three-mode capability. A sigmoid blending control is implemented for transition control, and an optimization routine is performed to improve the transition sequence based on performance goals. The optimized parameters are experimentally verified and shown to improve altitude variation and throttle usage compared to baseline.
ADVANCED INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Theory & Methods
Michael Jones, Soufiene Djahel, Kristopher Welsh
Summary: Unmanned aerial vehicles (UAVs) have the potential to be used in various scenarios where relying on human labor is risky or costly. Fleet of autonomous UAVs that can collaborate and independently manage their flight and tasks will create new opportunities but also pose research and regulatory challenges. Improvements in UAV construction, computing hardware, communication mechanisms, and sensors make it technically possible to commercially deploy fleets of autonomous UAVs.
ACM COMPUTING SURVEYS
(2023)
Review
Engineering, Aerospace
Jia Song, Kai Zhao, Yang Liu
Summary: This review article provides an update on the progress of the Mission Planning Problem (MPP) on Multi-UAV, focusing on the burning issue of task assignment. It compares the characteristics of mathematical programming method, heuristic algorithm, negotiation algorithm, and neural networks. The paper discusses different trajectory planning approaches and introduces common collaborative guidance methods. It emphasizes the need for ongoing research, addressing timeliness of task assignment, information coupling, and problems caused by multiple constraints and environmental uncertainty in MPP.
Article
Agricultural Engineering
Martina Mammarella, Lorenzo Comba, Alessandro Biglia, Fabrizio Dabbene, Paolo Gay
Summary: Fully-autonomous vehicles, both aerial and ground, have great potential in the Agriculture 4.0 framework, especially when operating within cooperative architectures. They are capable of tackling difficult tasks in complex and unstructured scenarios, such as vineyards on sloped terrains. A decentralised multi-phase approach is proposed as an alternative to common cooperative schemes. In this study, the approach is applied to a specific case study involving a vineyard, demonstrating improved autonomous driving capabilities and automated map retrieval for navigation by aerial and ground drones.
BIOSYSTEMS ENGINEERING
(2022)
Article
Agricultural Engineering
Martina Mammarella, Lorenzo Comba, Alessandro Biglia, Fabrizio Dabbene, Paolo Gay
Summary: Agriculture 4.0 uses technologies such as sensors, information systems, enhanced machinery, and informed management to optimize production by considering variabilities and uncertainties in agricultural systems. This study analyzes and understands the technical and methodological challenges involved, presents cooperative schemes and vehicle models for collaborative machines in agricultural scenarios, and provides an overview of state-of-the-art technologies for autonomous drone guidance. The application of these techniques in a case study in sloped vineyards is also reported.
BIOSYSTEMS ENGINEERING
(2022)
Article
Computer Science, Information Systems
Xiangyu Wu, Shuxiao Chen, Koushil Sreenath, Mark W. Mueller
Summary: This study proposes a perception-aware collision avoidance trajectory planner for multicopters, which can be used with any feature-based VIO algorithm. The planner samples and evaluates minimum jerk trajectories to find collision-free paths. It considers both motion blur of features and their locations for perception quality. The proposed method can run in real-time and has been validated through experiments in indoor and outdoor environments. It outperforms perception-agnostic planners in terms of accuracy, feature retention, and obstacle avoidance.
Article
Chemistry, Multidisciplinary
Carlos Villasenor, Alberto A. Gallegos, Gehova Lopez-Gonzalez, Javier Gomez-Avila, Jesus Hernandez-Barragan, Nancy Arana-Daniel
Summary: The research introduces a path planning algorithm based on ellipsoidal maps for UAVs, approximating the distance between ellipsoidal surfaces using a neural network due to the lack of a closed formula. The algorithm accurately represents the environment and computes paths for small UAVs, suitable for dynamic environments without increasing computational costs.
APPLIED SCIENCES-BASEL
(2021)
Article
Remote Sensing
Sitong Zhang, Yibing Li, Fang Ye, Xiaoyu Geng, Zitao Zhou, Tuo Shi
Summary: Unmanned Aerial Vehicles (UAVs) are crucial for collecting and transmitting data from remote areas, and collision-free navigation is essential for their successful operation. Existing methods for UAV collision avoidance face challenges such as high energy consumption and limited sensing ability. To address these challenges, we propose a hybrid collision-avoidance method that combines human-in-the-loop deep reinforcement learning (HL-DRL) and global planning. This method has been evaluated in simulated environments and has shown rapid adaptation and the ability to prevent UAVs from getting stuck in complex environments.
Article
Robotics
Ping Zhong, Bolei Chen, Siyi Lu, Xiaoxi Meng, Yixiong Liang
Summary: This paper proposes an information-driven exploration strategy for Unmanned Aerial Vehicles (UAVs) in unknown environments, utilizing the fast marching method. The strategy includes frontier point detection, evaluation of candidate goals based on a utility function, and optimization of UAV trajectory and yaw angle. Simulation experiments demonstrate the superiority of the proposed strategy.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Julius A. Marshall, Robert B. Anderson, Wen-Yu Chien, Eric N. Johnson, Andrea L'Afflitto
Summary: This paper introduces an original guidance system for multi-rotor unmanned aerial vehicles, enabling tactical behavior in potentially hostile environments. The system minimizes exposure to opponents and trajectory predictability while completing assigned tasks. By tuning parameters and utilizing onboard cameras and measurement units, the system demonstrates applicability in real-time scenarios.
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
(2021)
Article
Computer Science, Information Systems
Feng Shan, Jianping Huang, Runqun Xiong, Fang Dong, Junzhou Luo, Suyang Wang
Summary: Unmanned aerial vehicles (UAVs) have diverse applications in collecting data, monitoring facilities, and supporting mobile edge computing. This paper proposes a problem called the general waypoint-based PoI-visiting problem, aiming at minimizing flight energy consumption. The paper pays special attention to the energy consumption for turning and switching operations, and transforms the problem into the classic graph problem of the traveling salesman problem. The proposed algorithm is evaluated through simulations, showing promising results in terms of energy consumption.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Himanshu Gupta, K. Sreelakshmy, Om Prakash Verma, Tarun Kumar Sharma, Chang Wook Ahn, Kapil Kumar Goyal
Summary: Due to recent technological innovations, unmanned aerial vehicles (UAVs) are being increasingly utilized in various civil and military applications, including healthcare. However, most existing research only considers uniform obstacles, limiting their practicality. In this study, an improved algorithm combining Archimedes optimization algorithm (AOA) with grey wolf optimizer (GWO) and reinforcement learning (RL) is proposed, which demonstrates superior performance in terms of convergence speed and solution quality compared to other metaheuristics. The algorithm's effectiveness is further validated through rigorous experimentation on real-world 3D-route estimation problems for UAVs.
Article
Chemistry, Analytical
Jing Zhang, Jiwu Li, Hongwei Yang, Xin Feng, Geng Sun
Summary: This paper addresses the challenges of safe flying in complex urban environments for unmanned aerial vehicles through the use of BS-RRT for global path planning and RMGM(1,1) for predicting flight paths of dynamic obstacles, achieving faster convergence speed, higher stability, and more accurate trajectory predictions. The proposed algorithms provide effective solutions for path planning in urban environments with narrow passages and few dynamic flight obstacles.
Article
Computer Science, Hardware & Architecture
Irina Pustokhina, Denis A. Pustokhin, E. Laxmi Lydia, Mohamed Elhoseny, K. Shankar
Summary: This paper develops an Energy Efficient Neuro-Fuzzy Cluster based Topology Construction with Metaheuristic Route Planning (EENFC-MRP) algorithm for UAVs, which is proven to be superior in terms of energy efficiency compared to existing models through a series of simulation processes.