E2CoPre: Energy Efficient and Cooperative Collision Avoidance for UAV Swarms with Trajectory Prediction

03/11/2023

∙

This paper addresses the collision avoidance problem of UAV swarms in three-dimensional (3D) space. The key challenges are energy efficiency and cooperation of swarm members. We propose to combine Artificial Potential Field (APF) with Particle Swarm Planning (PSO). APF provides environmental awareness and implicit coordination to UAVs. PSO searches for the optimal trajectories for each UAV in terms of safety and energy efficiency by minimizing a fitness function. The fitness function exploits the advantages of the Active Contour Model in image processing for trajectory planning. Lastly, vehicle-to-vehicle collisions are detected in advance based on trajectory prediction and are resolved by cooperatively adjusting the altitude of UAVs. Simulation results demonstrate that our method can save up to 80% of energy compared to state-of-the-art schemes.

READ FULL TEXT

E2CoPre: Energy Efficient and Cooperative Collision Avoidance for UAV Swarms with Trajectory Prediction

E^2Coop: Energy Efficient and Cooperative Obstacle Detection and Avoidance for UAV Swarms

Multi-UAV Collision Avoidance using Multi-Agent Reinforcement Learning with Counterfactual Credit Assignment

Multi-Agent Deep Reinforcement Learning For Optimising Energy Efficiency of Fixed-Wing UAV Cellular Access Points

Optimal Trajectory Planning and Task Assignment for UAV-assisted Fog Computing

Obstacle Avoidance of Resilient UAV Swarm Formation with Active Sensing System in the Dense Environment

Energy-Efficient Cooperative Caching in UAV Networks

Feasible Computationally Efficient Path Planning for UAV Collision Avoidance

E2CoPre: Energy Efficient and Cooperative Collision Avoidance for UAV Swarms with Trajectory Prediction

Related Research

E^2Coop: Energy Efficient and Cooperative Obstacle Detection and Avoidance for UAV Swarms

Multi-UAV Collision Avoidance using Multi-Agent Reinforcement Learning with Counterfactual Credit Assignment

Multi-Agent Deep Reinforcement Learning For Optimising Energy Efficiency of Fixed-Wing UAV Cellular Access Points

Optimal Trajectory Planning and Task Assignment for UAV-assisted Fog Computing

Obstacle Avoidance of Resilient UAV Swarm Formation with Active Sensing System in the Dense Environment

Energy-Efficient Cooperative Caching in UAV Networks

Feasible Computationally Efficient Path Planning for UAV Collision Avoidance