Improvement of Decentralized Flocking Flight Efficiency of Fixed-Wing UAVs Using Inactive Agents

Song, Yeongho; Choi, Joonwon; Oh, Hyondong; Lee, Min; Lim, Seunghan; Lee, Jaemoon

doi:10.2514/6.2019-0391

Cited by 3 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Model-based approaches to solving the multi-vehicle flocking problem continue to be studied in the literature [21], [23], [29], [33], [36], [47]. These approaches involve formulating the kinematic and dynamic behaviors of the system in the environment.…”

Section: A Model-based Flockingmentioning

confidence: 99%

Implementation of Decentralized Reinforcement Learning-Based Multi-Quadrotor Flocking

et al. 2021

View full text Add to dashboard Cite

Enabling coordinated motion of multiple quadrotors is an active area of research in the field of small unmanned aerial vehicles (sUAVs). While there are many techniques found in the literature that address the problem, these studies are limited to simulation results and seldom account for wind disturbances. This paper presents the experimental validation of a decentralized planner based on multi-objective reinforcement learning (RL) that achieves waypoint-based flocking (separation, velocity alignment, and cohesion) for multiple quadrotors in the presence of wind gusts. The planner is learned using an object-focused, greatest mass, state-action-reward-state-action (OF-GM-SARSA) approach. The Dryden wind gust model is used to simulate wind gusts during hardware-in-the-loop (HWIL) tests. The hardware and software architecture developed for the multi-quadrotor flocking controller is described in detail. HWIL and outdoor flight tests results show that the trained RL planner can generalize the flocking behaviors learned in training to the real-world flight dynamics of the DJI M100 quadrotor in windy conditions.

show abstract

Section: A Model-based Flockingmentioning

confidence: 99%

Implementation of Decentralized Reinforcement Learning-Based Multi-Quadrotor Flocking

et al. 2021

View full text Add to dashboard Cite

show abstract

“…We extend the above inactiveness concept to the flocking task of fixed-wing UAVs. To find the best inactiveness level for each flock member, social learning particle swarm optimization (SL-PSO) [8] is applied as the first step by using the initial condition of the flock and building upon our previous work [29,18].…”

Section: Introductionmentioning

confidence: 99%

Using Lazy Agents to Improve the Flocking Efficiency of Multiple UAVs

Song

Choi

et al. 2021

J Intell Robot Syst

Self Cite

View full text Add to dashboard Cite

A group of agents can form a flock using the augmented Cucker-Smale (C-S) model. The model autonomously aligns them to a common velocity and maintains a relative distance among the agents in a distributed manner by sharing the information among neighbors. This paper introduces the concept of inactiveness to the augmented C-S model for improving the flocking performance. It involves controlling the energy and convergence time required to form a stable flock. Inspired by the natural world where a few lazy (or inactive) workers are helpful to the group performance in social insect colonies. In this study, we analyzed different levels of inactiveness as a degree of control input effectiveness for multiple fixed-wing UAVs in the flocking algorithm. To find the appropriate inactiveness level for each flock member, the particle swarm optimization-based approach is used as the first step, based on the initial condition of the flock.However, as the significant computational burden may cause difficulties in implementing the optimization-based approach in real time, we also propose a

show abstract

PPO-Exp: Keeping Fixed-Wing UAV Formation with Deep Reinforcement Learning

Guo

et al. 2022

Drones

View full text Add to dashboard Cite

Flocking for fixed-Wing Unmanned Aerial Vehicles (UAVs) is an extremely complex challenge due to fixed-wing UAV’s control problem and the system’s coordinate difficulty. Recently, flocking approaches based on reinforcement learning have attracted attention. However, current methods also require that each UAV makes the decision decentralized, which increases the cost and computation of the whole UAV system. This paper researches a low-cost UAV formation system consisting of one leader (equipped with the intelligence chip) with five followers (without the intelligence chip), and proposes a centralized collision-free formation-keeping method. The communication in the whole process is considered and the protocol is designed by minimizing the communication cost. In addition, an analysis of the Proximal Policy Optimization (PPO) algorithm is provided; the paper derives the estimation error bound, and reveals the relationship between the bound and exploration. To encourage the agent to balance their exploration and estimation error bound, a version of PPO named PPO-Exploration (PPO-Exp) is proposed. It can adjust the clip constraint parameter and make the exploration mechanism more flexible. The results of the experiments show that PPO-Exp performs better than the current algorithms in these tasks.

show abstract

Improvement of Decentralized Flocking Flight Efficiency of Fixed-Wing UAVs Using Inactive Agents

Cited by 3 publications

References 20 publications

Implementation of Decentralized Reinforcement Learning-Based Multi-Quadrotor Flocking

Implementation of Decentralized Reinforcement Learning-Based Multi-Quadrotor Flocking

Using Lazy Agents to Improve the Flocking Efficiency of Multiple UAVs

PPO-Exp: Keeping Fixed-Wing UAV Formation with Deep Reinforcement Learning

Contact Info

Product

Resources

About