Distributed 3-D Path Planning for Multi-UAVs with Full Area Surveillance Based on Particle Swarm Optimization

Abstract

Collision-free distributed path planning for the swarm of unmanned aerial vehicles (UAVs) in a stochastic and dynamic environment is an emerging and challenging subject for research in the field of a communication system. Monitoring the methods and approaches for multi-UAVs with full area surveillance is needed in both military and civilian applications, in order to protect human beings and infrastructure, as well as their social security. To perform the path planning for multiple unmanned aerial vehicles, we propose a trajectory planner based on Particle Swarm Optimization (PSO) algorithm to derive a distributed full coverage optimal path planning, and a trajectory planner is developed using a dynamic fitness function. In this paper, to obtain dynamic fitness, we implemented the PSO algorithm independently in each UAV, by maximizing the fitness function and minimizing the cost function. Simulation results show that the proposed distributed path planning algorithm generates feasible optimal trajectories and update maps for the swarm of UAVs to surveil the entire area of interest.

Distributed Search Planning in 3-D Environments With a Dynamically Varying Number of Agents

“…More recently, the authors in [22] proposed a decentralized MPC approach for multi-UAV trajectory planning for obstacle avoidance, whereas in [23] a consensus algorithm for distributed cooperative formation trajectory planning is proposed based on artificial potential fields and consensus theory. In [24] a samplingbased chance-constrained 2D trajectory planning approach is proposed for multiple UAV agents with probabilistic geofencing constraints, whereas in [25] a particle-swarm optimization (PSO) approach is proposed for distributed collisionfree trajectory planning with a team of UAVs operating in stochastic environments. More recently, the authors in [26] have proposed a deep reinforcement learning based 3D area coverage approach with a swarm of UAV agents, whereas in [27] a multi-robot coverage approach is proposed based on spatial graph neural networks.…”

Multi‐UAV path planning utilizing the PGA algorithm for terrestrial IoT sensor network under ISAC framework

“…Using the optimization approach, we built trajectory in 3D space from a sequence of waypoints. As a result, vector form is employed for encoding feasible paths, with the vector element $$$ {P}_i $$$ = ($$$ {a}_i,{b}_i,{c}_i $$$) representing the i th waypoint, 35 as shown below: $$$$ {P}_r={P}_1,{P}_2,{P}_3,\dots, {P}_{N_t} $$$$ where $$$ {N}_t $$$ is known as the number of trajectories in a feasible path.…”

“…Estimating the risk of flying can be represented RF as follows: $$$$ RF=\frac{\sum_{i=1}^{N_w-1}{RF}_i}{maxRF} $$$$ $$$$ {RF}_i={\varphi}_{ER}{r}_{i,i+1}^e+{\varphi}_{HAR}{r}_{i,i+1}^{ha} $$$$ where $$$ {\varphi}_{HAR} $$$ stands for high altitude risk and $$$ {\varphi}_{ER} $$$ for environmental risk, $$$ {RF}_i $$$is the flight risk prediction can be calculate from the i th waypoint to the ( i + 1 )th waypoint. We normalized the estimated flight risk and came up with the formula max FRE 35 : $$$$ maxRF=\left({N}_w-1\right)\times \Big[{\varphi}_{HAR}\times Z+{\varphi}_{ER}\times \left(2\mathit{\max}{r}^e\right) $$$$ …”

“…Using the optimization approach, we built trajectory in 3D space from a sequence of waypoints. As a result, vector form is employed for encoding feasible paths, with the vector element P i = (a i , b i , c i ) representing the ith waypoint, 35 as shown below:…”

Multi-Destination Path Planning Method Research of Mobile Robots Based on Goal of Passing through the Fewest Obstacles

“…They can plan a collision-free travel route [2]. Traditional path planning methods for mobile robots include artificial potential field method [3], fuzzy logic algorithm [4], genetic algorithm [5], particle swarm optimization algorithm [6] and so on. The traditional path planning algorithm is mainly single-destination path planning.…”