Unmanned Systems · 2018 · 213 citations · 127 references
EngineeringAerospace EngineeringAutonomous SystemsAerial RoboticsPath PlanningRoboticsAutonomous NavigationNavigation PlanningObstacle AvoidanceRobot NavigationSense-and-avoid SystemsAerial Obstacle AvoidanceExact AlgorithmsLocal Obstacle AvoidanceMotion Planning With Obstacle AvoidanceNavigationTrajectory PlanningUav NavigationUnmanned Aerial Vehicle Navigation
Unmanned aerial vehicles are increasingly studied for civilian use, yet current navigation systems lack robust sense‑and‑avoid capabilities essential for safe operation, prompting research into heuristic and non‑heuristic path‑planning algorithms. This paper conducts a comprehensive comparative analysis of UAV path‑planning algorithms across both heuristic and non‑heuristic categories. The authors evaluate the algorithms in 3‑D environments with sensor noise and real‑time constraints, testing them on three obstacle scenarios and varying the availability of global and local obstacle data. The study reveals that computational time and solution optimality vary with the type of obstacle information available, highlighting trade‑offs among the algorithms.
Unmanned aerial vehicles (UAVs) have recently attracted the attention of researchers due to their numerous potential civilian applications. However, current robot navigation technologies need further development for efficient application to various scenarios. One key issue is the “Sense and Avoid” capability, currently of immense interest to researchers. Such a capability is required for safe operation of UAVs in civilian domain. For autonomous decision making and control of UAVs, several path-planning and navigation algorithms have been proposed. This is a challenging task to be carried out in a 3D environment, especially while accounting for sensor noise, uncertainties in operating conditions, and real-time applicability. Heuristic and non-heuristic or exact techniques are the two solution methodologies that categorize path-planning algorithms. The aim of this paper is to carry out a comprehensive and comparative study of existing UAV path-planning algorithms for both methods. Three different obstacle scenarios test the performance of each algorithm. We have compared the computational time and solution optimality, and tested each algorithm with variations in the availability of global and local obstacle information.
127
Reinforcement Learning: An Introduction
Richard S. Sutton, Andy Barto · IEEE Transactions on Neural Networks · 1998 · 27.1K citations
A note on two problems in connexion with graphs
E. Dijkstra · Numerische Mathematik · 1959 · 23.8K citations
Adhi Harmoko S, M.Komp, Joseph Marie Jacquard et al. · 2005 · 18.4K citations
Learning to Predict by the Methods of Temporal Differences
Richard S. Sutton · Machine Learning · 1988 · 4K citations · Full text