Algorithm for energy efficient inter-UAV collision avoidance

Abeywickrama, Hasini Viranga; Jayawickrama, Beeshanga Abewardana; He, Ying; Dutkiewicz, Eryk

doi:10.1109/iscit.2017.8261200

Cited by 27 publications

(13 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As commonly done in the literature ( [10], [4]), a safety distance (L) is defined for the UAVs. When two or more UAVs are closer than the safety distance to each other, it is identified as a collision (Fig.…”

Section: ) Collision Detectionmentioning

confidence: 99%

“…Additional complications arise when multiple UAV-BSs are deployed to serve a specific geographical area. Multiple UAVs sharing a common air space, flying in close proximity to each other, increase the possibility of inter-UAV collisions [4]. Furthermore, due to the same reasons, the probability of interference to ground users from the neighbouring cells (UAV-BSs) increases considerably.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Reinforcement Learning Approach for Fair User Coverage Using UAV Mounted Base Stations Under Energy Constraints

Abeywickrama

Dutkiewicz

et al. 2020

IEEE Open J. Veh. Technol.

Self Cite

View full text Add to dashboard Cite

Unmanned Aerial Vehicles (UAVs) are gaining popularity in many aspects of wireless communication systems. UAV-mounted mobile base stations (UAV-BSs) are an effective and costefficient solution for providing wireless connectivity where fixed infrastructure is not available or destroyed. However, UAV-BSs have their limitations and complications, for instance, limited available energy. In addition, when several UAV-BSs are deployed to provide coverage to a specific area, the possibility of inter-UAV collisions and the interference to ground users increase. We propose Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) based methods to deploy UAV-BSs under energy constraints to provide efficient and fair coverage to the ground users, while minimising inter-UAV collisions and interference to ground users. The proposed methods outperform the baseline methods by an average increase of 38.94% in system fairness, 42.54% in individual user coverage, and 15.04% in total system coverage, in comparison with the baseline methods. INDEX TERMS Unmanned aerial vehicles (UAVs), wireless coverage, reinforcement learning.

show abstract

Section: ) Collision Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Reinforcement Learning Approach for Fair User Coverage Using UAV Mounted Base Stations Under Energy Constraints

Abeywickrama

Dutkiewicz

et al. 2020

IEEE Open J. Veh. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although real‐time experiments were conducted successfully and it could be seen that a possible collision between two vehicles is prevented, this method still needs to be extended to crashes involving more than two vehicles. A potential field method was used in [16, 30] to achieve inter‐unmanned aerial vehicle (UAV) collision avoidance using a virtual repulsive force derived from the negative gradient of a potential function. The force calculating method may cause oscillations in the trajectory or even getting stuck due to local minima [31].…”

Section: Introductionmentioning

confidence: 99%

“…Despite these shortcomings, the current NI technique can be improved to address some problems of formation control with collision avoidance for networked SNI systems interacting on directed network topologies. For example, in order to switch into an obstacle avoidance formation, the relative positions in a specified formation are changed gradually based on the NI consensus‐based formation tracking controller and a novel geometric method, so that oscillations/disturbances in the obstacle avoidance trajectories are avoided, which is one of the main obstacles in [16, 30]. Next, the NI formation control strategy can be easily connected to the other NI control protocols while the internal stability and synchronous characteristic of the fully distributed control structure are still naturally guaranteed.…”

Section: Introductionmentioning

confidence: 99%

Switching formation strategy with the directed dynamic topology for collision avoidance of a multi‐robot system in uncertain environments

Tran

Garratt

Petersen

2020

IET Control Theory & Appl

View full text Add to dashboard Cite

“…Unmanned Aerial Vehicles (UAV) are fast becoming a popular choice for a wide variety of commercial applications. Their many desirous features like the ability to hover, the ability to fly over dangerous and inaccessible areas and ease of deployment enable UAVs to be widely used in many aspects of social life [1].…”

Section: Introductionmentioning

confidence: 99%

Empirical Power Consumption Model for UAVs

Abeywickrama

Jayawickrama

et al. 2018

2018 IEEE 88th Vehicular Technology Conference (VTC-Fall)

Self Cite

View full text Add to dashboard Cite

Unmanned Aerial Vehicles (UAV) are gaining popularity in a range of areas and are already being used for a wide variety of purposes. While UAVs have many desirable features, limited battery lifetime is identified as a key restriction in UAV applications. Typical UAVs being electric devices, powered by on-board batteries, this constrain has limited their capabilities to a considerable extent. Thus planning UAV missions in an energy efficient manner is of utmost importance. To achieve this, for prediction of power consumption, it is necessary to have a reliable power consumption model. In this paper, we present a consistent and complete power consumption model for UAVs based on empirical studies of battery usage for various UAV activities. The power consumption model presented in this paper can be readily used for energy efficient UAV mission planning.

show abstract

Algorithm for energy efficient inter-UAV collision avoidance

Cited by 27 publications

References 7 publications

A Reinforcement Learning Approach for Fair User Coverage Using UAV Mounted Base Stations Under Energy Constraints

A Reinforcement Learning Approach for Fair User Coverage Using UAV Mounted Base Stations Under Energy Constraints

Switching formation strategy with the directed dynamic topology for collision avoidance of a multi‐robot system in uncertain environments

Empirical Power Consumption Model for UAVs

Contact Info

Product

Resources

About