A novel unmanned aerial vehicle path planning approach: sand cat optimization algorithm incorporating learned behaviour

Abstract

Unmanned aerial vehicle(UAV) path planning plays an important role in UAV flight, and an effective algorithm is needed to realize UAV path planning. The sand cat algorithm is characterized by simple parameter setting and easy implementation. However, the convergence speed is slow, easy to fall into the local optimum. In order to solve these problems, a novel sand cat algorithm incorporating learning behaviors (LSCSO) is proposed. LSCSO is inspired by the life habits and learning ability of sand cats and incorporates a new position update strategy into the basic Sand Cat Optimization Algorithm, which maintains the diversity of the population and improves the convergence ability during the optimization process. Finally, LSCSO is applied to the challenging UAV 3D path planning with cubic B-spline interpolation to generate a smooth path, and the proposed algorithm is compared with a variety of other competing algorithms. The experimental results show that LSCSO has excellent optimization-seeking ability and plans a safe and feasible path with minimal cost consideration among all the compared algorithms.

Research on mobile robot path planning in complex environment based on DRQN algorithm

“…The expected value function of a mobile robot in a certain state s is expressed as shown in equation (8). Considering the effect that action a brings to the intelligent body, the action value function ( ) p q s a , is introduced, as shown in equation (9).…”

“…Path planning methods can be divided into two categories based on environment information, location point search, and constraints: conventional and reinforcement learning methods [8]. Conventional methods can be further divided into rule-based and heuristic search traditional methods, represented by A * and dynamic window algorithms [9]; graphical methods based on geometry and graph theory, represented by raster methods and Voronoi diagrams [10,11]; intelligent biomimetic algorithms based on the foraging and evolution of organisms, represented by swarms of bees, beetles, and sparrows [12]. The above methods have different advantages, but all have limited utilization of environmental information and poor path planning in unknown and dynamic environments.…”

A New Autonomous Method of Drone Path Planning Based on Multiple Strategies for Avoiding Obstacles with High Speed and High Density

“…At present, in the field of path planning research, scholars from various countries are concentrating on improving the efficiency, completeness, and optimality of search paths. The achievements made are mainly divided into graph search algorithms [2][3][4][5][6][7], fluid/potential field algorithms [8][9][10][11][12][13][14], heuristic algorithms [15][16][17][18][19], and artificial intelligence learning algorithms. Graph search is the most effective search method for finding the shortest path in the static road network.…”

“…However, the algorithm lacks global information, making it only suitable for obstacle avoidance in local space. Reference [17] proposed a sand cat algorithm with learning behavior, which enables the UAV to plan a safe and feasible path at low cost. However, heuristic algorithms are typically suitable for simple or small environments.…”