相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Automation & Control Systems
Zhikai Yao et al.
Summary: This article introduces a new model-based reinforcement learning controller to improve the control performance of hydraulic systems. By using a recursive robust integral control approach and an actor-critic structure in the reinforcement learning approach, the proposed controller is able to achieve high-accuracy tracking and asymptotic stability guarantees at the system level.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2023)
Review
Chemistry, Analytical
Sabitri Poudel et al.
Summary: Advancements in electronics and software have led to the rapid development of unmanned aerial vehicles (UAVs) and their applications. Path planning is a crucial aspect of UAV communications, and bio-inspired algorithms have emerged as a potential solution. However, there is currently no survey on the existing bio-inspired algorithms for UAV path planning. This study investigates and compares various bio-inspired algorithms extensively, highlighting their key features, working principles, advantages, and limitations. It also discusses the challenges and future trends in UAV path planning.
Article
Computer Science, Theory & Methods
Michael Jones et al.
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)
Article
Computer Science, Artificial Intelligence
Jiahua Wang et al.
Summary: This paper proposes a novel two-stage deep reinforcement learning method for multi-UAV decision-making. It uses a sample generator combining artificial potential field with proportional-integral-derivative to produce expert experience data. The method introduces a two-stage reinforcement learning training method, where the policy network and critic network are pre-trained using expert data and then the excellent experience generated by the agent itself is used to guide the policy network, improving the efficiency of data utilization. Extensive simulation experiments demonstrate that the proposed method enables multi-UAV to continuously track the target in obstacle environments and significantly improves learning speed and convergence effect.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Information Systems
Ahmed Alagha et al.
Summary: This study proposes two novel multi-agent deep reinforcement learning models for target localization through search in complex environments. The first model utilizes proximal policy optimization, convolutional neural networks, Convolutional AutoEncoders, and breadth first search to obtain cooperative agents for fast and low-cost localization. The second model improves computational complexity by replacing the shaped reward with a simple sparse reward, using Expert Demonstrations to guide the learning of new agents. The proposed models are tested on a scenario of radioactive target localization and benchmarked against existing methods, showing efficacy in terms of localization time, cost, learning speed, and stability.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Proceedings Paper
Engineering, Aerospace
Christos Chronis et al.
Summary: Autonomous Beyond Visual Line of Sight (BVLOS) Unmanned Aerial Vehicles (UAVs) with high-performance obstacle avoidance and navigation algorithms are capable of successfully navigating in unknown environments. The research findings demonstrate that using low-cost distance sensors, it is possible to navigate the drone around obstacles.
12TH EASN INTERNATIONAL CONFERENCE ON INNOVATION IN AVIATION & SPACE FOR OPENING NEW HORIZONS
(2023)
Article
Engineering, Aerospace
Wei Jiang et al.
Summary: This study proposes a 3D path planning and collision avoidance algorithm for unmanned aerial vehicles (UAVs) based on Partially Observable Markov Decision Process (POMDP) and improved grey wolf optimizer (GWO). The algorithm plans a flyable path using the improved GWO with level comparison (GWOLC) and models aircraft collision avoidance as POMDP. Simulation experiments demonstrate the effectiveness and robustness of the proposed algorithm.
AEROSPACE SCIENCE AND TECHNOLOGY
(2022)
Review
Engineering, Electrical & Electronic
Abhishek Sharma et al.
Summary: This paper focuses on the path planning problem for intercepting multiple aerial targets using a swarm of UAVs, with a comprehensive review of Swarm Intelligence algorithms applied in this context. The paper evaluates each algorithm by analyzing its merits and demerits, providing scholars and professionals in the field with an overview of current research in UAV swarm technology.
IETE TECHNICAL REVIEW
(2022)
Article
Remote Sensing
H. B. Makineci et al.
Summary: This study optimizes the impact of input parameters on outputs of UAV photogrammetry using artificial neural networks, and identifies that atmospheric conditions significantly affect battery status and flight time. The normalization process plays a crucial role in optimization.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2022)
Article
Engineering, Aerospace
Xiaowei Fu et al.
Summary: This paper proposes a UAV pursuit-evasion strategy based on DDPG and imitation learning. By using imitation learning to improve the exploration strategy of DDPG, the algorithm's exploration efficiency is increased, avoiding useless exploration. The simulation results show that the improved DDPG algorithm is more effective in improving training efficiency.
INTERNATIONAL JOURNAL OF AEROSPACE ENGINEERING
(2022)
Article
Engineering, Marine
Misganaw Abebe et al.
Summary: This study proposes a hybrid ARIMA-LSTM model for predicting ship trajectories using AIS data, addressing the limitations of previous approaches in terms of accuracy and complexity. The results demonstrate that the proposed model can accurately estimate near-future trajectories and evaluate collision risks.
Proceedings Paper
Automation & Control Systems
Matthias Huppi et al.
Summary: In this work, a novel sampling-based path-planning algorithm called Temporal-PRM is proposed to avoid obstacles in dynamic environments. The algorithm extends the original Probabilistic Roadmap (PRM) with the notion of time and uses a time-aware variant of the A* search algorithm to efficiently query the path. Experimental results show that the proposed path planner outperforms other state-of-the-art sampling-based solvers and can run onboard a flying robot in real-time.
2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
(2022)
Article
Computer Science, Information Systems
Tianrui Zhang et al.
Summary: This article studies hybrid path planning models, such as multi-robot path planning and formation cooperative control, to solve the problem of insufficient task execution capability of a single robot under complex conditions. By improving the particle swarm algorithm and the artificial potential field method, global and local path planning models are proposed to enhance the path exploration capability and handling efficiency of robot formation.
Article
Computer Science, Artificial Intelligence
Victoria J. Hodge et al.
Summary: Mobile robots like drones play a crucial role in surveillance, monitoring, and data collection in buildings, infrastructure, and environments. The research aims to achieve accurate and rapid problem localization through flexible, autonomous, and powerful decision-making mobile robots. The implementation of a generic adaptive navigation algorithm using deep reinforcement learning algorithms aims to improve accuracy and efficiency.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Y. Volkan Pehlivanoglu et al.
Summary: This paper addresses the path planning problem of autonomous UAV in target coverage problems using artificial intelligent methods such as genetic algorithm, ant colony optimizer, Voronoi diagram, and clustering methods. The proposed enhancement methods in GA accelerate the convergence process, while the integration of collision points of cluster centers provides the best result in avoiding crashes with terrain surfaces.
APPLIED SOFT COMPUTING
(2021)
Article
Engineering, Aerospace
Yujin Shin et al.
Summary: Traditional path generation algorithms often assume accurate knowledge of user and obstacle positions, but in reality, positioning accuracy can vary due to different factors. The proposed method in this study utilizes a blend of potential and positioning risk fields to generate a hybrid directional flow for safe and efficient path planning for unmanned vehicles.
AEROSPACE SCIENCE AND TECHNOLOGY
(2021)
Article
Computer Science, Hardware & Architecture
Mahmoud Hussein et al.
Summary: This paper presents key technologies supporting the development of drone systems, emphasizing their impact on economy, environment, and human life risks. It also discusses the contributions of the COMP4DRONES project towards improving existing technologies.
MICROPROCESSORS AND MICROSYSTEMS
(2021)
Article
Robotics
Julian Ibarz et al.
Summary: Deep reinforcement learning has shown promise in enabling physical robots to learn complex skills in the real world, which presents numerous challenges in perception and movement. Real-world robotics provides a unique domain for evaluating deep RL algorithms, addressing challenges that are often overlooked in mainstream RL research.
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH
(2021)
Article
Chemistry, Analytical
Eulalia Balestrieri et al.
Summary: The paper presents a classification of UAV safety solutions found in scientific literature, highlighting the fundamental role of sensors and measurements in this field. The proposed solutions cover a range of areas including flight test procedures, in-flight solutions, fault and damage detection, collision avoidance, safe landing, as well as ground solutions for testing and injury and damage quantification measurements.
Review
Computer Science, Artificial Intelligence
Mohammad Moshref-Javadi et al.
Summary: Research on drone-based logistics models focuses on classification and comprehensive review to identify future research directions; existing studies mainly focus on e-commerce and healthcare, while other application areas require further exploration.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Farzad Kiani et al.
Summary: This study presents three novel versions of a hybrid method to assist autonomous robots in three-dimensional path planning. By improving the RRT algorithm and utilizing metaheuristic algorithms, these methods play an important role in selecting the next stations and generating optimal paths. Simulation results demonstrate the superior performance of these methods in UAV path planning compared to other algorithms.
NEURAL COMPUTING & APPLICATIONS
(2021)
Proceedings Paper
Automation & Control Systems
Yunlong Song et al.
Summary: This research introduces a new approach to near-time-optimal trajectory generation for quadrotors using deep reinforcement learning and relative gate observations. The method is capable of computing near-time-optimal trajectories and adapting to changes in the environment, showing computational advantages over traditional trajectory optimization methods. The approach is evaluated on race tracks in simulation and with a physical quadrotor, achieving speeds of up to 60 km/h.
2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
(2021)
Article
Engineering, Civil
Abhik Singla et al.
Summary: This paper presents a method for enabling a UAV quadrotor to autonomously avoid collisions with obstacles in unstructured and unknown indoor environments. The method, based on deep reinforcement learning, uses recurrent neural networks with temporal attention and outperforms prior works in terms of distance covered without collisions. Additionally, the technique reduces power wastage by minimizing oscillatory motion of the UAV.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Marcel Menner et al.
Summary: This paper introduces a method for inverse learning of a control objective defined in terms of requirements and their joint probability distribution. Parametrized requirements and methods for estimating their parameters are also proposed. Results suggest that the proposed model and learning method enable a more natural and personalized driving style for autonomous vehicles.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2021)
Review
Automation & Control Systems
Daniel Ioan et al.
Summary: This paper reviews the past and current results and approaches in motion planning using Mixed-integer Programming (MIP). It highlights the efficiency of MIP in selecting from a limited number of alternatives or solving optimization problems over non-convex domains, as well as the importance of various experimental validations in the literature.
ANNUAL REVIEWS IN CONTROL
(2021)
Article
Computer Science, Information Systems
Yanli Chen et al.
Summary: This study proposes an improved ACO-APF algorithm for path planning of USVs, which combines ant colony optimization and artificial potential field algorithms to enhance efficiency and safety in dynamic environments.
Article
Automation & Control Systems
Bianca Sangiovanni et al.
Summary: This letter proposes a hybrid control methodology utilizing Deep Reinforcement Learning to train robot manipulators to avoid obstacles while performing tasks. A switching mechanism is enabled when close to obstacles, allowing for automatic adjustments to cope with unexpected objects in the workspace. The proposal was tested on a realistic robot manipulator simulated in a V-REP environment.
IEEE CONTROL SYSTEMS LETTERS
(2021)
Article
Computer Science, Artificial Intelligence
Chao Yan et al.
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
(2020)
Review
Computer Science, Information Systems
Shubhani Aggarwal et al.
COMPUTER COMMUNICATIONS
(2020)
Article
Computer Science, Artificial Intelligence
Chengzhi Qu et al.
KNOWLEDGE-BASED SYSTEMS
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Harald Bayerlein et al.
2020 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM)
(2020)
Proceedings Paper
Automation & Control Systems
Wei Wang et al.
PROCEEDINGS OF 2020 IEEE 4TH INFORMATION TECHNOLOGY, NETWORKING, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (ITNEC 2020)
(2020)
Article
Computer Science, Information Systems
Bo Li et al.
Article
Engineering, Electrical & Electronic
Ursula Challita et al.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2019)
Article
Computer Science, Artificial Intelligence
Ram Kishan Dewangan et al.
APPLIED INTELLIGENCE
(2019)
Article
Robotics
Su Yeon Choi et al.
Article
Computer Science, Information Systems
Lanxiang Zheng et al.
Article
Computer Science, Information Systems
Yubing Wang et al.
Proceedings Paper
Computer Science, Information Systems
Yunpeng Xu et al.
PROCEEDINGS OF 2019 IEEE 9TH INTERNATIONAL CONFERENCE ON ELECTRONICS INFORMATION AND EMERGENCY COMMUNICATION (ICEIEC 2019)
(2019)
Article
Computer Science, Information Systems
Hao Jiang et al.
Article
Computer Science, Information Systems
Zhenyu Wu et al.
Article
Robotics
Przemyslaw Mariusz Kornatowski et al.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2018)
Article
Robotics
Jan Faigl et al.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2018)
Review
Engineering, Aerospace
M. Hassanalian et al.
PROGRESS IN AEROSPACE SCIENCES
(2017)
Article
Engineering, Aerospace
Mohammadreza Radmanesh et al.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART G-JOURNAL OF AEROSPACE ENGINEERING
(2016)
Article
Engineering, Aerospace
Peng Yao et al.
AEROSPACE SCIENCE AND TECHNOLOGY
(2016)
Article
Engineering, Aerospace
Peng Yao et al.
AEROSPACE SCIENCE AND TECHNOLOGY
(2015)
Article
Multidisciplinary Sciences
Volodymyr Mnih et al.
Article
Automation & Control Systems
Celine Teuliere et al.
IEEE TRANSACTIONS ON CYBERNETICS
(2015)
Article
Engineering, Aerospace
Shankarachary Ragi et al.
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
(2013)
Article
Engineering, Aerospace
Jung Leng Foo et al.
JOURNAL OF AEROSPACE COMPUTING INFORMATION AND COMMUNICATION
(2009)
Article
Automation & Control Systems
Priyadarshi Bhattacharya et al.
IEEE ROBOTICS & AUTOMATION MAGAZINE
(2008)